© 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 · 68494 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
68494

INDEX

Explanations

way

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

.GraphicsUnit

-0.08

Dr

-0.07

,private

-0.07

Dr

-0.07

yecto

-0.07

请大家

-0.07

.sigmoid

-0.07

MJ

-0.07

insn

-0.07

엪

-0.06

POSITIVE LOGITS

 Flood

0.07

榖

0.07

洪水

0.07

努

0.07

↵

0.06

 Supply

0.06

 continu

0.06

 Universal

0.06

 начала

0.06

Roc

0.06

Activations Density 0.004%

No Known Activations