© 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 · 57392 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
57392

INDEX

Explanations

AB

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

~>

-0.08

dip

-0.07

(att

-0.07

ѕ

-0.07

EMP

-0.07

 newX

-0.07

PUT

-0.06

 thử

-0.06

-tip

-0.06

 Meditation

-0.06

POSITIVE LOGITS

ведения

0.08

焉

0.07

iling

0.07

 Canucks

0.07

햠

0.07

勤奋

0.07

cta

0.07

$('

0.07

.BO

0.07

.RecyclerView

0.07

Activations Density 0.001%

No Known Activations