© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN3.5-9B-PT · 15-QWENSCOPE-RES-64K · 30083 ｜ Neuronpedia

Home
Qwen3.5-9B Base
15-QWENSCOPE-RES-64K
30083

INDEX

Explanations

haiyan, smethwick, vallentyne

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

Äįkih

-0.08

³

-0.08

·

-0.07

Äįkog

-0.07

izo

-0.07

à¸łà¸²à¸ŀ

-0.07

à¸«à¸±à¸ª

-0.07

cze

-0.07

Äįku

-0.07

µ

-0.07

POSITIVE LOGITS

en

0.13

à¦¨

0.13

à¸±à¸Ļ

0.13

à¤¨

0.12

äººè¯´

0.12

×Ł

0.12

mann

0.12

an

0.12

ÙĬÙĨ

0.12

äººåľ¨

0.12

Activations Density 1.539%

No Known Activations