© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN3.5-9B-PT · 15-QWENSCOPE-RES-64K · 46524 ｜ Neuronpedia

Home
Qwen3.5-9B Base
15-QWENSCOPE-RES-64K
46524

INDEX

Explanations

despite

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

“

-0.12

âĢ

-0.10

Âł

-0.10

’

-0.10

-0.09

’s

-0.08

 (“

-0.08

 toward

-0.08

**

-0.08

 âĨĴ

-0.07

POSITIVE LOGITS

à¸£à¸±à¸Ļ

0.09

Lastly

0.09

 swiftly

0.08

entiel

0.08

çĬ¹å¦Ĥ

0.08

 proprietor

0.08

:...

0.08

 ailments

0.08

 querying

0.08

 swift

0.08

Activations Density 0.062%

No Known Activations