© 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

QWEN3.5-9B-PT · 15-QWENSCOPE-RES-64K · 24449 ｜ Neuronpedia

Home
Qwen3.5-9B Base
15-QWENSCOPE-RES-64K
24449

INDEX

Explanations

for exampleinstance

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

Prompts (Dashboard)

24,576 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

ako

-0.06

 either

-0.06

ä¸ºè¯¥

-0.06

 sustaining

-0.06

åĶ¯

-0.06

-0.06

çļĦæ¨¡æł·

-0.05

çĶĦ

-0.05

ulis

-0.05

å°±ç®Ĺæĺ¯

-0.05

POSITIVE LOGITS

elaar

0.10

 pairs

0.09

å¯¹ä¸ĢäºĽ

0.09

éħįå¯¹

0.09

gnore

0.09

 pair

0.08

ä¾ĭåŃĲ

0.08

pairs

0.08

 cáº·p

0.08

agung

0.08

Activations Density 0.124%

No Known Activations