© 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 · 15-RESID-POST-AA · 23348 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
23348

INDEX

Explanations

e

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

dig

-0.07

㌠

-0.06

 viene

-0.06

.Token

-0.06

Room

-0.06

 Welch

-0.06

 בעוד

-0.06

.IsSuccess

-0.06

sum

-0.06

icts

-0.06

POSITIVE LOGITS

bred

0.08

 (�

0.08

(:,

0.08

 ruby

0.07

_orientation

0.07

 steroids

0.07

 hãy

0.07

الأردن

0.07

.removeListener

0.07

뗐

0.07

Activations Density 0.000%

No Known Activations