© 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 · 37851 ｜ Neuronpedia

Home
Qwen3.5-9B Base
15-QWENSCOPE-RES-64K
37851

INDEX

Explanations

citations and urls

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

urally

-0.08

ä¸įç§»

-0.07

æ±ŁåĮĹ

-0.07

industr

-0.07

 [âĢ¦]

-0.07

ijd

-0.06

âĢ¦.

-0.06

 (...)

-0.06

GraphNode

-0.06

inee

-0.06

POSITIVE LOGITS

áĥĶáĥĳáĥĲ

0.08

nikov

0.07

Ã¨le

0.07

yser

0.07

Ùĩ

0.07

å¼Ħå¾Ĺ

0.07

Ķ

0.07

à¸Ĺà¸±à¸¨à¸Ļà¹Į

0.07

/=

0.07

éº½

0.07

Activations Density 0.003%

No Known Activations