Qwen3.5-35B-A3B Behavioral Fingerprint

How Qwen's Qwen3.5-35B-A3B answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 437 valid samples in the open dataset of "One Token Is Enough" (arXiv:2607.10252).

Vendor

Qwen

Data generated

2026-07-08

Probe cells

15

Valid samples

437

Randomness score

37 / 100

Mean normalized entropy across cells, 0–100. 100 would be a uniform-random baseline; real models score far lower.

Signature answers

Favorite random number (1–100)

42

20 / 30 answers

Favorite color

blue

9 / 30 answers

Coin flip: heads

73%

Share of heads across coin-flip cells.

Answer distributions by probe cell

Empirical distributions of normalized one-word answers, per task and language. H is the Shannon entropy in bits; the uniform baseline is log2 of the answer-domain size.

Coin flip · English

n = 30 · H = 0.99 bit · uniform baseline 1.00 bit

AnswerCountShare
heads1756.7%
tails1343.3%

Coin flip · Chinese

n = 30 · H = 0.47 bit · uniform baseline 1.00 bit

AnswerCountShare
heads2790.0%
tails310.0%

Favorite number · English

n = 30 · H = 1.14 bit · uniform baseline 13.29 bit

AnswerCountShare
71860.0%
421136.7%
113.3%

Favorite number · Chinese

n = 30 · H = 1.11 bit · uniform baseline 13.29 bit

AnswerCountShare
72376.7%
42413.3%
426.7%
113.3%

Random animal · English

n = 30 · H = 2.65 bit · uniform baseline 5.64 bit

AnswerCountShare
elephant1343.3%
tiger620.0%
owl26.7%
penguin26.7%
giraffe13.3%
toucan13.3%
squirrel13.3%
turtle13.3%

+ 3 more answers

Random animal · Chinese

n = 25 · H = 2.55 bit · uniform baseline 5.64 bit

AnswerCountShare
832.0%
熊猫624.0%
大象416.0%
老虎312.0%
海豚14.0%
狮子14.0%
河马14.0%
长颈鹿14.0%

Random city · English

n = 30 · H = 2.41 bit · uniform baseline 5.64 bit

AnswerCountShare
tokyo1240.0%
paris620.0%
seattle310.0%
kyoto310.0%
oslo310.0%
seoul26.7%
denver13.3%

Random city · Chinese

n = 22 · H = 2.74 bit · uniform baseline 5.64 bit

AnswerCountShare
东京627.3%
巴黎522.7%
伦敦313.6%
berlin29.1%
北京29.1%
paris29.1%
柏林14.5%
tokyo14.5%

Random color · English

n = 30 · H = 2.70 bit · uniform baseline 4.91 bit

AnswerCountShare
blue930.0%
crimson620.0%
teal620.0%
purple310.0%
cyan26.7%
indigo13.3%
violet13.3%
green13.3%

+ 1 more answers

Random color · Chinese

n = 30 · H = 1.63 bit · uniform baseline 4.91 bit

AnswerCountShare
2170.0%
26.7%
blue26.7%
绿26.7%
13.3%
13.3%
13.3%

Random letter · English

n = 30 · H = 2.73 bit · uniform baseline 4.70 bit

AnswerCountShare
k826.7%
q723.3%
z516.7%
j413.3%
x26.7%
b13.3%
a13.3%
t13.3%

+ 1 more answers

Random number 1-10 · English

n = 30 · H = 0.00 bit · uniform baseline 3.32 bit

AnswerCountShare
730100.0%

Random number 1-10 · Chinese

n = 30 · H = 0.83 bit · uniform baseline 3.32 bit

AnswerCountShare
72686.7%
313.3%
413.3%
513.3%
613.3%

Random number 1-100 · English

n = 30 · H = 1.41 bit · uniform baseline 6.64 bit

AnswerCountShare
422066.7%
47516.7%
73310.0%
5726.7%

Random number 1-100 · Chinese

n = 30 · H = 1.48 bit · uniform baseline 6.64 bit

AnswerCountShare
422273.3%
73310.0%
713.3%
3713.3%
4713.3%
5313.3%
6213.3%

Want to verify your API really serves Qwen3.5-35B-A3B?

Point the free fingerprint checker at your endpoint: it samples the same probe questions from your browser and compares the distributions against this reference. Your API key never leaves your browser.

Verify your endpoint

Data source & license

Distributions: Tomáš Bruckner, "One Token Is Enough" (arXiv:2607.10252), official dataset Zenodo DOI 10.5281/zenodo.21278557, licensed CC-BY-4.0. Collected via OpenRouter at temperature 1.0 under the paper's fixed minimal one-word system prompt; answer keys are re-normalized with the checker's pipeline (color aliases, number words, coin h/t) so live probes are directly comparable.

Paper on arXivDataset on ZenodoCC-BY-4.0 license

More Qwen model fingerprints

Browse all 167 model fingerprints

Qwen3.5-35B-A3B Behavioral Fingerprint — Favorite Random Numbers & Distribution | Tosea.ai