© 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 · 18361 ｜ Neuronpedia

Home
Qwen3.5-4B
15-RES-MATRYOSHKA-65K
18361

INDEX

Explanations

actions and goals

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

åī§

-0.06

ç¥

-0.06

 Progr

-0.06

aner

-0.06

Vol

-0.06

elon

-0.06

çŁ«

-0.05

ebol

-0.05

osg

-0.05

kra

-0.05

POSITIVE LOGITS

sus

0.05

inders

0.05

ì°°

0.05

 their

0.05

its

0.05

å¤ļçĤ¹

0.05

åĽ¾æĸ¯

0.05

umente

0.05

eel

0.05

Bia

0.05

Activations Density 0.030%

No Known Activations