© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

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

QWEN2.5-7B-IT · 19-RESID-POST-AA · 2989 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
2989

INDEX

Explanations

of

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

ลงทะเบ

-0.07

堇

-0.07

公网安备

-0.07

 Previously

-0.07

樊

-0.07

 taxpayer

-0.06

,’

-0.06

odesk

-0.06

ClearColor

-0.06

iliation

-0.06

POSITIVE LOGITS

什么叫

0.07

断

0.07

Height

0.07

Hillary

0.07

识

0.07

味

0.07

\ActiveForm

0.07

甚么

0.06

هر

0.06

wire

0.06

Activations Density 0.248%

No Known Activations