© 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 · 32147 ｜ Neuronpedia

Home
Qwen3.5-9B Base
15-QWENSCOPE-RES-64K
32147

INDEX

Explanations

No Explanations Found

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

per

-0.07

aul

-0.07

ju

-0.06

Î¸Î®

-0.06

ulsion

-0.06

ipro

-0.06

irk

-0.06

keep

-0.06

-0.06

ä¸ŃæĹ¬

-0.06

POSITIVE LOGITS

æ¯Ķçħ§

0.09

aix

0.08

 terperinci

0.08

stv

0.08

uw

0.08

uib

0.08

hr

0.08

aro

0.07

èªł

0.07

 INLINE

0.07

Activations Density 0.000%

No Known Activations