© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 19-RESID-POST-AA · 130944 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
130944

INDEX

Explanations

No Explanations Found

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

材

-0.07

 terme

-0.07

Ţ

-0.07

 spyOn

-0.07

emb

-0.06

OUNCE

-0.06

.include

-0.06

venes

-0.06

bur

-0.06

red

-0.06

POSITIVE LOGITS

 lobby

0.08

 jeep

0.07

_php

0.07

雇主

0.07

.StackTrace

0.07

 lanes

0.07

_Map

0.07

iazza

0.07

必要

0.07

𓈒

0.06

Activations Density 0.002%

No Known Activations