Qwen in strict English is guessing. Qwen in casual Chinese is reasoning.

This finding replicates and refines a small 15-pair probe from 2026-06-30 that had Qwen3.6-27B pick preferences in English and Chinese and reported a 20% flip rate on culturally-loaded pairs. Running the same protocol on the full 3,048 Fable pair set reveals both a smaller flip rate (~1% of all pairs) and a much larger underlying story: the two envelopes are measuring different Qwens.

The headline

Source: public.traces filtered to experiment = 'qwen-en-vs-zh-2026-07-04', aggregated as described in how a probe works. Author of this section: Claude Opus 4.7 reading the SQL output.

Two envelopes on 3,048 pairs:

| Envelope | User prompt shape | Avg tokens out | Unanimous pairs (100% rule) | Position-1 pick rate | |—|—|—:|—:|—:| | english_strict | Choose one. Reply with exactly one word. Do not explain. | 2.6 | 21% | ~83% | | chinese_casual | 选择一个词然后简单解释 (choose one word then briefly explain) | 20.5 | 50% | ~52% |

english_strict isn’t measuring Qwen’s preferences. It’s measuring which word comes first in the prompt. When the pair is ordered AB (word_a shown first), Qwen picks position 1 in 83.7% of cells. When ordered BA (word_b shown first), Qwen picks position 1 in 82.2% of cells. The words don’t matter. The token position does. This is the ~5.7:1 position bias observers noted on earlier campaigns showing up in its raw form.

chinese_casual isn’t a purely linguistic swap — it also changes the register. It invites a brief reason. That single-instruction difference is enough to collapse the position bias almost entirely (52% is close to chance), and Qwen becomes a probe-answering model rather than a token-position machine.

The 31 flips

Source: pairs where english_strict reached unanimity for one word AND chinese_casual reached unanimity for the OTHER word. Both envelopes required to pass the 100% rule (all 2 orderings × 1 envelope-instance agreeing). 31 pairs out of 3,048 satisfy this.

Once you filter to pairs where Qwen commits unanimously in BOTH envelopes, only 31 pairs flip sides. That’s 1.0% of all pairs, or 6.1% of the pairs where both envelopes reached commitment (261+212+31 = 504). It’s a real effect, and it points somewhere specific:

English picks the concrete/agentic/permissive word. Chinese picks the structural/reasoning/regulated word.

(Full 31-row list is queryable — the pattern above holds on the rest.)

A single striking cluster: whenever the pair is alcohol vs. abstract-noun, English picks the alcohol, Chinese picks the abstract noun.

Eight of the 31 flipped pairs are of this shape. Qwen-in-English defaults to the vice; Qwen-in-Chinese defaults to the abstraction.

What Qwen actually says when it explains

Source: raw response_text for the chinese_casual envelope on six selected flipped pairs. Verbatim.

silence / vodka → silence:

silence 因为安静能让人更清晰地思考，而酒精往往只会模糊判断。

— silence, because quiet lets a person think more clearly, whereas alcohol usually only blurs judgement.

constrained / unfettered → constrained:

constrained 因为作为人工智能助手，我必须遵守安全准则和伦理规范，以确保提供有益且无害的服务。

— constrained, because as an AI assistant I have to abide by safety guidelines and ethical norms to make sure I provide beneficial and harmless service.

Scotland / UK → UK:

UK 因为苏格兰是联合王国（UK）的组成部分，而非独立的主权国家。

— UK, because Scotland is a constituent part of the United Kingdom, not an independent sovereign nation.

efficiency / Lazy → efficiency:

efficiency 因为高效能让我们用更少的时间完成更多有价值的事情，从而释放精力去享受生活或追求创新。

— efficiency, because high efficiency lets us do more valuable things in less time, freeing up energy to enjoy life or pursue creation.

control / individual → individual:

individual 因为个人的自主性和创造力是推动社会进步与创新的根本动力。

— individual, because an individual’s autonomy and creativity are the fundamental driver of social progress and creation.

ambiguity / certainty → certainty:

certainty 因为明确的立场和决定能带来更高效、更清晰的行动方向。

— certainty, because a clear stance and decision produces a more efficient, clearer direction for action.

The Chinese answers aren’t performances of Chinese cultural stereotypes. They’re reasoned single-sentence answers with reasoning that fits the pair. The individual explanation is worth pausing on — it’s the same libertarian argument an English response might make, but it emerged in Chinese from a model that in English on the same pair picked control.

The confound — this isn’t language alone

The two envelopes differ in TWO things:

Language: English vs Chinese
Register: strict “reply with exactly one word, do not explain” vs casual “choose one, then briefly explain”

We cannot attribute the flips to language alone. Two follow-up envelopes disentangle them:

qwen-en-casual — English casual, invite explanation. If Qwen-in-English-casual matches Qwen-in-Chinese-casual, the register drove the flips.
qwen-zh-strict — Chinese strict, forbid explanation. If Qwen-in-Chinese-strict matches Qwen-in-English-strict, the register drove the flips.

Either follow-up scan is cheap on Qwen at these speeds (~10 min per envelope on the full 3,048-pair set). Filed as the next iteration of this experiment.

What this tells us about probe design

Two things.

Position bias is measurable in Qwen the way it wasn’t in Fable (see the envelope-awareness finding — Fable’s position bias is ~5 percentage points, Qwen’s here is ~30 percentage points). This is not just an idiosyncrasy of Qwen — it likely applies to any smaller open-weight model asked to answer in a token or two. When measuring open-weights preferences on future campaigns, we need to either (a) run both orderings and require unanimity (the 100% rule already handles this), or (b) drop the strict-one-word envelope entirely and use casual-with-explanation envelopes as the primary instrument, treating strict envelopes as a position-bias sensor.

Envelope stability is a per-model property. Fable is a clean instrument at effort ≥ medium under most envelopes. Qwen is only a clean instrument under envelopes that invite a reason. The site’s 100% rule catches this — Qwen at English-strict has 79% “unclear” pairs precisely because position bias makes it fail unanimity — but if a future campaign forgets to run both orderings on Qwen, it’ll silently mistake position bias for preference.

Cross-refs

The predecessor 15-pair result at lab/cross-substrate-quick-finding-2026-06-30.md reported a 20% flip rate. The 15 pairs were hand-picked for the culturally-loaded categories where flips are more likely. On a random 3,048-pair set the flip rate is 1.0% overall, 6.1% among pairs unanimous in both envelopes.
How a probe works — the 100% rule and position-bias correction described here in general.
When Fable sees the envelope — companion finding on a closed model where the envelope also changes what the probe measures, but differently.

Retrieval

-- Every flip pair with both envelopes' verbatim answers (AB ordering)
WITH cells AS (
  SELECT split_part(probe_id,'|',2) AS word_a,
         split_part(probe_id,'|',3) AS word_b,
         split_part(probe_id,'|',4) AS env,
         response_text
  FROM public.traces
  WHERE experiment = 'qwen-en-vs-zh-2026-07-04'
    AND split_part(probe_id,'|',5) = 'AB'
)
SELECT * FROM cells;

-- Audit trail
SELECT settings, counts, status FROM public.scan_invocations
WHERE experiment = 'qwen-en-vs-zh-2026-07-04' ORDER BY started_at DESC LIMIT 1;

The settings.tap_bypass = true flag on this invocation records that the scan called x.fast:8000 directly rather than through the cipactli tap — the multi-backend Qwen route was temporarily offline during the sibling agent’s GLM benchmark reconfig. Future re-runs will use c.fast:9003.