© 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 · 19-RESID-POST-AA · 68565 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
68565

INDEX

Explanations

develop

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

公认

-0.08

 صف

-0.08

	TArray

-0.07

tearDown

-0.07

تعلق

-0.07

主营业务

-0.07

 Specific

-0.07

 بطري

-0.07

 TArray

-0.07

.ExecuteReader

-0.07

POSITIVE LOGITS

Aw

0.07

asy

0.07

atra

0.07

 chảy

0.07

 çıkan

0.07

 absent

0.07

NX

0.06

的話

0.06

 surf

0.06

襦

0.06

Activations Density 0.023%

No Known Activations