© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

QWEN2.5-7B-IT · 19-RESID-POST-AA · 70541 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
70541

INDEX

Explanations

)

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

($)

-0.07

 States

-0.07

ş

-0.07

-0.07

早日

-0.07

 registros

-0.07

に関する

-0.07

一封

-0.07

�

-0.06

 customary

-0.06

POSITIVE LOGITS

-sided

0.07

關於

0.07

 absol

0.07

麻痹

0.07

 Visible

0.07

 analyses

0.07

 setIs

0.07

.tmp

0.07

Widget

0.07

 Winn

0.06

Activations Density 0.041%

No Known Activations