AI Desk · AI Fingerprinting · Evidence object
Tokenizer signature tk_06ffa14a
An exact tokenizer signature: every model listed below returned the same marginal prompt-token count on all 50 test strings. Sharing a signature is strong evidence of a shared vocabulary. This signature sits in the Qwen · group C group.
- Members
- 6
- First observed
- 21 August 2026
- Last observed
- 5 October 2026
- Group
- Qwen · group C
Models with this signature
Apodex: Apodex 1.1 Mini (free)apodex/apodex-1.1-mini:freeApodexKwaipilot: KAT-Coder-Air V2.5kwaipilot/kat-coder-air-v2.5KwaipilotNex AGI: Nex-N2.5-Pronex-agi/nex-n2.5-proNex AgiQwen: Qwen3.6 27Bqwen/qwen3.6-27bAlibaba (Qwen)Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3bAlibaba (Qwen)Qwen: Qwen3.8 27Bqwen/qwen3.8-27bAlibaba (Qwen)
Template variants of the same tokenizer
These signatures differ from this one by a uniform one-token shift on the affected strings: the same vocabulary behind a different chat template.
The measured vector
Marginal prompt-token cost per string, as measured on Apodex: Apodex 1.1 Mini (free)All 50 rows
English and whitespace
en-prose14
en-long16
spaces-203
spaces-603
tabs-203
newlines-204
mixed-ws5
Digits
digits-99
digits-1212
digits-3030
digits-sep12
float-long22
CJK
zh-common9
zh-long10
zh-rare18
ja-kana7
ja-kanji10
ko13
Other scripts
ru12
ar10
he14
hi20
th12
el13
Emoji
emoji-basic9
emoji-skin30
emoji-zwj-family18
emoji-zwj-x354
emoji-flags24
emoji-prof29
Rare Unicode
math29
boxdraw28
combining5
cjk-ext-b13
surrogates40
zalgo36
rtl-mix6
Code
py-code26
py-indent18
json25
html16
regex44
camel5
snake6
Repetition and encodings
rare-word-x530
repeat-tok21
base6436
hex17
url19
uuid36
Method: tokenizer fingerprinting, v1-50.