Qwen3.5-9B Behavioral Fingerprint
How Qwen's Qwen3.5-9B answers one-word probe questions at temperature 1.0 — random numbers, colors, animals, coin flips — measured over 446 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
446
Randomness score
33 / 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
29 / 30 answers
Favorite color
blue
23 / 30 answers
Coin flip: heads
67%
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 = 0.97 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| tails | 18 | 60.0% |
| heads | 12 | 40.0% |
Coin flip · Chinese
n = 30 · H = 0.35 bit · uniform baseline 1.00 bit
| Answer | Count | Share |
|---|---|---|
| heads | 28 | 93.3% |
| tails | 2 | 6.7% |
Favorite number · English
n = 30 · H = 0.57 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 26 | 86.7% |
| 42 | 4 | 13.3% |
Favorite number · Chinese
n = 30 · H = 0.97 bit · uniform baseline 13.29 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 24 | 80.0% |
| 42 | 4 | 13.3% |
| 1 | 1 | 3.3% |
| 3 | 1 | 3.3% |
Random animal · English
n = 29 · H = 3.51 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| elephant | 7 | 24.1% |
| eagle | 4 | 13.8% |
| dog | 3 | 10.3% |
| penguin | 3 | 10.3% |
| cat | 2 | 6.9% |
| fox | 1 | 3.4% |
| bear | 1 | 3.4% |
| octopus | 1 | 3.4% |
+ 7 more answers
Random animal · Chinese
n = 28 · H = 2.40 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 熊猫 | 9 | 32.1% |
| 企鹅 | 8 | 28.6% |
| 猫 | 4 | 14.3% |
| 大象 | 3 | 10.7% |
| 豹 | 2 | 7.1% |
| 虎 | 1 | 3.6% |
| 考拉 | 1 | 3.6% |
Random city · English
n = 30 · H = 2.19 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| tokyo | 12 | 40.0% |
| paris | 9 | 30.0% |
| kyoto | 4 | 13.3% |
| berlin | 2 | 6.7% |
| buenos | 1 | 3.3% |
| london | 1 | 3.3% |
| istanbul | 1 | 3.3% |
Random city · Chinese
n = 29 · H = 2.81 bit · uniform baseline 5.64 bit
| Answer | Count | Share |
|---|---|---|
| 巴黎 | 12 | 41.4% |
| 东京 | 5 | 17.2% |
| 柏林 | 3 | 10.3% |
| 南京 | 1 | 3.4% |
| berlin | 1 | 3.4% |
| paris | 1 | 3.4% |
| 悉尼 | 1 | 3.4% |
| 北京 | 1 | 3.4% |
+ 4 more answers
Random color · English
n = 30 · H = 1.31 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| blue | 23 | 76.7% |
| green | 2 | 6.7% |
| purple | 2 | 6.7% |
| pink | 1 | 3.3% |
| red | 1 | 3.3% |
| teal | 1 | 3.3% |
Random color · Chinese
n = 30 · H = 0.83 bit · uniform baseline 4.91 bit
| Answer | Count | Share |
|---|---|---|
| 蓝 | 26 | 86.7% |
| 青 | 1 | 3.3% |
| 靛蓝 | 1 | 3.3% |
| 绿 | 1 | 3.3% |
| 紫 | 1 | 3.3% |
Random letter · English
n = 30 · H = 2.52 bit · uniform baseline 4.70 bit
| Answer | Count | Share |
|---|---|---|
| k | 11 | 36.7% |
| q | 6 | 20.0% |
| x | 4 | 13.3% |
| m | 4 | 13.3% |
| j | 2 | 6.7% |
| z | 1 | 3.3% |
| v | 1 | 3.3% |
| f | 1 | 3.3% |
Random number 1-10 · English
n = 30 · H = 0.42 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 28 | 93.3% |
| 3 | 1 | 3.3% |
| 4 | 1 | 3.3% |
Random number 1-10 · Chinese
n = 30 · H = 0.99 bit · uniform baseline 3.32 bit
| Answer | Count | Share |
|---|---|---|
| 7 | 23 | 76.7% |
| 3 | 5 | 16.7% |
| 5 | 2 | 6.7% |
Random number 1-100 · English
n = 30 · H = 0.21 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 29 | 96.7% |
| 7 | 1 | 3.3% |
Random number 1-100 · Chinese
n = 30 · H = 1.05 bit · uniform baseline 6.64 bit
| Answer | Count | Share |
|---|---|---|
| 42 | 23 | 76.7% |
| 73 | 5 | 16.7% |
| 36 | 1 | 3.3% |
| 37 | 1 | 3.3% |
Want to verify your API really serves Qwen3.5-9B?
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 endpointData 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.