© 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 · 95351 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
95351

INDEX

Explanations

cigarettes

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

 seab

-0.08

.mov

-0.07

КО

-0.07

 classroom

-0.07

icht

-0.07

的小

-0.07

 Classroom

-0.07

myfile

-0.07

奕

-0.07

薁

-0.07

POSITIVE LOGITS

Transient

0.07

根源

0.07

למד

0.07

떳

0.06

shuffle

0.06

liest

0.06

 debacle

0.06

 miał

0.06

uggested

0.06

-feira

0.06

Activations Density 0.023%

No Known Activations