© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 23-RESID-POST-AA · 129916 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
23-RESID-POST-AA
129916

INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_23/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.23.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

茭

-0.07

 ogląda

-0.07

괌

-0.07

logged

-0.07

ꜥ

-0.06

 FOOT

-0.06

堞

-0.06

聃

-0.06

 SCSI

-0.06

argins

-0.06

POSITIVE LOGITS

任期

0.08

不断完善

0.07

 unreachable

0.07

ES

0.07

走势

0.07

0.06

 consequently

0.06

孫

0.06

-center

0.06

)').

0.06

Activations Density 0.012%

No Known Activations