© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 19-RESID-POST-AA · 5398 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
5398

INDEX

Explanations

Resumes/career objectives

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

MaxLength

-0.08

ࠓ

-0.07

 ActiveRecord

-0.07

(',',

-0.07

 permanent

-0.07

 textStatus

-0.07

phalt

-0.07

ideal

-0.07

clc

-0.07

##

-0.07

POSITIVE LOGITS

lrt

0.07

0.07

нят

0.07

 burst

0.07

gö

0.07

.Exchange

0.06

ŕ

0.06

缨

0.06

্

0.06

摇了

0.06

Activations Density 0.048%

No Known Activations