© 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 · 26538 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
26538

INDEX

Explanations

say "**"

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

 Humb

-0.07

ểu

-0.07

톨

-0.07

 ferr

-0.07

 Jail

-0.07

 tong

-0.07

bble

-0.07

�

-0.07

 brun

-0.07

 undercut

-0.06

POSITIVE LOGITS

toList

0.08

'}

0.07

'}}↵

0.07

//

0.07

 therapeutic

0.07

😍

0.07

 ''}↵

0.07

 there

0.07

;"↵

0.07

\<

0.06

Activations Density 0.005%

No Known Activations