© 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 · 7-RESID-POST-AA · 57552 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
57552

INDEX

Explanations

image

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

将近

-0.08

 setTimeout

-0.07

癫

-0.07

(payment

-0.07

بد

-0.07

逐步

-0.07

 абсолютно

-0.07

 phát

-0.07

Checkpoint

-0.07

而对于

-0.07

POSITIVE LOGITS

.Stretch

0.07

 ראשי

0.07

_unicode

0.07

璠

0.07

惯例

0.07

_ulong

0.07

 Fonts

0.07

LastError

0.07

ᄌ

0.06

 Nacht

0.06

Activations Density 0.009%

No Known Activations