© 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 · 20283 ｜ Neuronpedia

Home
Qwen3.5-9B Base
15-QWENSCOPE-RES-64K
20283

INDEX

Explanations

numbers and symbols

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

ouw

-0.09

AGER

-0.08

])]

-0.08

Ã¼b

-0.08

Ã¶rg

-0.08

eus

-0.08

lacer

-0.08

Ð¡Ð¢Ð¬

-0.08

cci

-0.08

kek

-0.08

POSITIVE LOGITS

ä½Ĩè¿Ļ

0.08

ä¼¼ä¹İ

0.08

ä½ĨéĤ£

0.07

 somehow

0.07

ä¼¼ä¹İåľ¨

0.06

But

0.06

But

0.06

ä¸įå¯¹

0.06

0.06

 something

0.06

Activations Density 0.002%

No Known Activations