© 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 · 7-RESID-POST-AA · 102853 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
102853

INDEX

Explanations

slam

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

xffff

-0.08

 varies

-0.08

 zdjęć

-0.07

OfFile

-0.07

腋

-0.07

_Main

-0.07

옵

-0.07

TIME

-0.07

)(__

-0.07

.embed

-0.07

POSITIVE LOGITS

等级

0.07

畖

0.07

ꡔ

0.07

 Grand

0.06

 prototypes

0.06

 formal

0.06

Wrapper

0.06

 авиа

0.06

人脸

0.06

/types

0.06

Activations Density 0.003%

No Known Activations