© 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 · 55567 ｜ Neuronpedia

Home
Qwen3.5-9B Base
15-QWENSCOPE-RES-64K
55567

INDEX

Explanations

And ... after text

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

ave

-0.08

ç½ĳé¦ĸé¡µ

-0.07

åĬĽå¼º

-0.07

åĵī

-0.07

ave

-0.07

ç«ĭåį³ä¸ĭè½½

-0.07

+'

-0.06

 orient

-0.06

/apis

-0.06

yl

-0.06

POSITIVE LOGITS

ÙĪÛĮÙĩ

0.08

ogenesis

0.08

èĭ¦è¾£

0.08

urus

0.07

NOP

0.07

chine

0.07

eel

0.07

leme

0.07

ëŀ

0.07

sit

0.07

Activations Density 0.001%

No Known Activations