© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

QWEN2.5-7B-IT · 11-RESID-POST-AA · 87992 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
87992

INDEX

Explanations

Pope

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Mark

-0.07

uffix

-0.07

List

-0.07

brush

-0.06

'?

-0.06

pls

-0.06

relative

-0.06

헣

-0.06

uz

-0.06

agner

-0.06

POSITIVE LOGITS

\Eloquent

0.09

 Pope

0.08

/Observable

0.08

(connect

0.07

/kernel

0.07

 ValidationResult

0.07

 Siemens

0.07

 Kant

0.07

といった

0.07

石化

0.07

Activations Density 0.002%

No Known Activations