© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

QWEN2.5-7B-IT · 11-RESID-POST-AA · 85644 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
85644

INDEX

Explanations

afraid

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

	height

-0.08

	PORT

-0.07

辒

-0.07

avascript

-0.07

 diret

-0.07

.DropDownStyle

-0.07

oud

-0.07

 amort

-0.06

Arizona

-0.06

	view

-0.06

POSITIVE LOGITS

 Counties

0.08

pcs

0.08

قانون

0.07

 Hoffman

0.07

 Swan

0.07

.format

0.07

的规定

0.07

Rule

0.07

erves

0.07

lassen

0.06

Activations Density 0.003%

No Known Activations