© 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 · 127659 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
127659

INDEX

Explanations

punctuation

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

 Coleman

-0.07

hè

-0.07

_f

-0.07

 economic

-0.06

お金を

-0.06

看

-0.06

BIO

-0.06

')(

-0.06

郜

-0.06

军团

-0.06

POSITIVE LOGITS

.Clone

0.07

 Attributes

0.07

RIPT

0.07

وج

0.07

/qu

0.07

.ds

0.06

(!$

0.06

 horas

0.06

 humanitarian

0.06

ятся

0.06

Activations Density 0.314%

No Known Activations