© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 15-RESID-POST-AA · 63433 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
63433

INDEX

Explanations

No Explanations Found

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

go

-0.09

Ac

-0.08

 Bloomberg

-0.07

 wreck

-0.07

Ctx

-0.07

ch

-0.07

re

-0.07

Tre

-0.07

(coeff

-0.07

vis

-0.07

POSITIVE LOGITS

솬

0.08

افت

0.07

rowCount

0.07

但不限

0.07

åde

0.07

_hand

0.07

ław

0.07

 pleasure

0.07

oat

0.07

.setMaximum

0.07

Activations Density 0.002%

No Known Activations