© 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 · 7-RESID-POST-AA · 56713 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
56713

INDEX

Explanations

balance

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

…..

-0.07

iesel

-0.07

.Logging

-0.07

 }}
↵

-0.07

`'

-0.07

(pf

-0.07

 BaseType

-0.07

ASS

-0.06

.So

-0.06

.Red

-0.06

POSITIVE LOGITS

甾

0.07

Criteria

0.06

บางคน

0.06

鲫

0.06

밨

0.06

 misconception

0.06

expérience

0.06

ifier

0.06

겴

0.06

ój

0.06

Activations Density 0.069%

No Known Activations