© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 75682 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
75682

INDEX

Explanations

amortization

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

ny

-0.08

쌨

-0.07

规定的

-0.07

_FINE

-0.07

 가지

-0.07

-org

-0.07

_different

-0.07

 awake

-0.07

冈

-0.07

_MUX

-0.07

POSITIVE LOGITS

 JsonResult

0.07

 nostro

0.07

本事

0.07

텄

0.07

/".$

0.07

💑

0.07

Tem

0.07

0.07

Benef

0.07

 initiated

0.07

Activations Density 0.002%

No Known Activations