© 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 · 76150 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
76150

INDEX

Explanations

milligrams

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

 Movies

-0.07

מד

-0.07

 Wonderland

-0.07

 curled

-0.07

_ARRAY

-0.07

نج

-0.07

#echo

-0.07

创伤

-0.07

 iter

-0.07

已在

-0.07

POSITIVE LOGITS

>Create

0.07

YES

0.07

長

0.06

>We

0.06

 weighed

0.06

 diferen

0.06

_black

0.06

pH

0.06

\(

0.06

 bishop

0.06

Activations Density 0.007%

No Known Activations