© 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 · 9388 ｜ Neuronpedia

Home
Qwen3.5-9B Base
15-QWENSCOPE-RES-64K
9388

INDEX

Explanations

scientific/medical terms

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

èŁĭ

-0.07

æ¶Ī

-0.07

èľ¡

-0.06

æĿ¥æ»¡è¶³

-0.06

AGMA

-0.06

à¸²à¸ļ

-0.06

Ø±Ø§

-0.06

ä¹ī

-0.06

lington

-0.06

ìĤ¼

-0.06

POSITIVE LOGITS

èĬ®

0.08

ongs

0.07

[âĢ¦

0.07

åľı

0.07

kest

0.07

ppe

0.07

onge

0.07

çĹŀ

0.07

 âĹİ

0.07

mig

0.07

Activations Density 0.065%

No Known Activations