© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN3.5-4B · 15-RES-MATRYOSHKA-65K · 17298 ｜ Neuronpedia

Home
Qwen3.5-4B
15-RES-MATRYOSHKA-65K
17298

INDEX

Explanations

numbers and symbols

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Configuration

decoderesearch/qwen-3.5-saes/qwen-3.5-4b

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

No Configuration Found

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

à¸§à¸¢

-0.07

wer

-0.07

Ð¶Ð½ÐµÐ¼Ñĥ

-0.07

åħ¬

-0.06

wak

-0.06

çī½

-0.06

kait

-0.06

à¹Ģà¸Ķà¸µà¸¢

-0.06

zol

-0.06

posit

-0.06

POSITIVE LOGITS

éĢļè¿ĩ

0.06

Ank

0.06

0.05

 through

0.05

ixin

0.05

ãĢįï¼Ī

0.05

éĢļéģİ

0.05

åĽł

0.05

(=

0.05

 compare

0.05

Activations Density 0.082%

No Known Activations