© 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 · 15-RESID-POST-AA · 49791 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
49791

INDEX

Explanations

by

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

隐形

-0.07

 adjunct

-0.07

 discern

-0.07

 spilled

-0.07

实施

-0.06

擐

-0.06

شاشة

-0.06

叠加

-0.06

 cyclist

-0.06

 recyclerView

-0.06

POSITIVE LOGITS

 cuatro

0.07

 Cuba

0.07

Broken

0.07

obre

0.07

ío

0.07

Std

0.07

BITS

0.07

AtIndex

0.07

篾

0.07

那一

0.07

Activations Density 0.001%

No Known Activations