© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 19-RESID-POST-AA · 59132 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
59132

INDEX

Explanations

also

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

Negative Logits

.Adam

-0.07

蓼

-0.07

trie

-0.07

典

-0.07

�

-0.07

Promise

-0.07

奄

-0.06

fur

-0.06

attles

-0.06

śmie

-0.06

POSITIVE LOGITS

="'+

0.07

Ả

0.07

{/*

0.07

 المدينة

0.07

婧

0.07

yclerView

0.06

مؤسسة

0.06

ировка

0.06

-break

0.06

0.06

Activations Density 0.178%

No Known Activations