© 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 · 13607 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
13607

INDEX

Explanations

#define

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

 newPath

-0.07

(function

-0.07

 trousers

-0.07

丝丝

-0.06

숭

-0.06

scene

-0.06

千年

-0.06

tones

-0.06

אמן

-0.06

bmp

-0.06

POSITIVE LOGITS

 Background

0.06

强制

0.06

Yeah

0.06

Everybody

0.06

.rightBarButtonItem

0.06

 Dispatch

0.06

Db

0.06

RX

0.06

边境

0.06

Gratis

0.06

Activations Density 0.004%

No Known Activations