© 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 · 11-RESID-POST-AA · 20904 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
20904

INDEX

Explanations

Name abbreviations

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

츠

-0.07

Tod

-0.07

CFO

-0.07

됍

-0.06

 admir

-0.06

rawing

-0.06

Repositories

-0.06

 arrival

-0.06

ntp

-0.06

FTC

-0.06

POSITIVE LOGITS

用于

0.07

(([

0.07

.ceil

0.07

是用来

0.07

.VALUE

0.06

Language

0.06

_ssh

0.06

集合

0.06

 conform

0.06

⊋

0.06

Activations Density 0.024%

No Known Activations