© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

QWEN3.5-4B · 15-RES-MATRYOSHKA-65K · 22533 ｜ Neuronpedia

Home
Qwen3.5-4B
15-RES-MATRYOSHKA-65K
22533

INDEX

Explanations

prime or composite

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

Negative Logits

blick

-0.06

oked

-0.06

&R

-0.06

alaus

-0.06

heard

-0.06

ilst

-0.06

Ð±ÐµÐ»ÑĮ

-0.06

çľĭåĪ°ä¸Ģä¸ª

-0.06

éĹ®åıĬ

-0.05

artner

-0.05

POSITIVE LOGITS

åĲĮæĹ¶

0.06

æ¯Ķ

0.06

æļĤæĹ¶

0.05

 Yours

0.05

0.05

ments

0.05

 unpopular

0.05

à¸ģà¹ĩà¸ķà¸²à¸¡

0.05

0.05

0.05

Activations Density 0.004%

No Known Activations