© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 7-RESID-POST-AA · 77851 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
77851

INDEX

Explanations

ag

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

(^

-0.08

 initialised

-0.08

Š

-0.07

bal

-0.06

.DAL

-0.06

stor

-0.06

ensagem

-0.06

נסה

-0.06

Cfg

-0.06

 chocolates

-0.06

POSITIVE LOGITS

 embedding

0.07

mark

0.07

 conform

0.07

commend

0.07

DateTime

0.07

덤

0.07

.toBe

0.06

旻

0.06

折射

0.06

تعليم

0.06

Activations Density 0.002%

No Known Activations