© 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 · 21650 ｜ Neuronpedia

Home
Qwen3.5-4B
15-RES-MATRYOSHKA-65K
21650

INDEX

Explanations

population counts

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

 Termine

-0.06

ä¸ĢéĢļ

-0.06

ä¸¤å¤Ħ

-0.06

 Roya

-0.06

ÑĥÐ´Ð°

-0.06

ering

-0.06

ä¸ľéĺ³

-0.06

è¯ł

-0.06

 Terrain

-0.06

çĻ½äºĨ

-0.06

POSITIVE LOGITS

åįķ

0.07

å¤ĸåĽ´

0.06

åįķä¸ª

0.06

åĮħ

0.06

åĽ´

0.06

ola

0.05

åıªçľĭ

0.05

 single

0.05

.single

0.05

åĮº

0.05

Activations Density 0.036%

No Known Activations