© 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

QWEN2.5-7B-IT · 19-RESID-POST-AA · 7596 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
7596

INDEX

Explanations

non-English words

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

 Guid

-0.07

 pain

-0.07

errMsg

-0.07

 parents

-0.07

($(

-0.07

 Wireless

-0.07

.jms

-0.07

fft

-0.07

 Colum

-0.07

 PUBLIC

-0.06

POSITIVE LOGITS

थ

0.09

 kullandı

0.07

Eyl

0.07

Zi

0.06

diğinde

0.06

 исследова

0.06

zi

0.06

 Buck

0.06

,node

0.06

 skóry

0.06

Activations Density 0.081%

No Known Activations