© 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 · 65154 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
65154

INDEX

Explanations

sensory perception

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

McB

-0.08

 prosecutions

-0.07

죔

-0.07

Vm

-0.07

 하는

-0.06

 Society

-0.06

有时候

-0.06

PushMatrix

-0.06

 Sampler

-0.06

 -->
↵
↵

-0.06

POSITIVE LOGITS

 parted

0.09

ói

0.07

颖

0.07

éis

0.07

reas

0.07

مول

0.07

ulis

0.06

 seams

0.06

quis

0.06

 bian

0.06

Activations Density 0.067%

No Known Activations