© 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 · 20191 ｜ Neuronpedia

Home
Qwen3.5-9B Base
15-QWENSCOPE-RES-64K
20191

INDEX

Explanations

suppose equations

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

otin

-0.10

enticate

-0.09

rhein

-0.09

ERAL

-0.08

ultats

-0.08

ÙĩØ±Ø¨

-0.08

oglio

-0.08

ained

-0.08

unno

-0.08

peror

-0.08

POSITIVE LOGITS

forth

0.09

aux

0.08

 forth

0.07

0.07

antha

0.07

zelfde

0.07

ä½łæĬĬ

0.07

fter

0.07

Ø§

0.07

lah

0.07

Activations Density 0.022%

No Known Activations