INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uÅŁ

-0.27

çĽ®

-0.27

Foot

-0.25

inston

-0.24

uler

-0.24

Ce

-0.24

ä¼łæĦŁåĻ¨

-0.24

å¤§å¹ħåº¦

-0.24

 Foot

-0.24

 Progress

-0.23

POSITIVE LOGITS

èģĺè¯·

0.29

 theirs

0.28

 yours

0.27

çħ§é¡¾

0.25

æħ§

0.25

Risk

0.24

æĢ»èµĦäº§

0.24

éĹ¨æĪ·

0.23

illage

0.22

æĪ·å¤ĸ

0.22

Activations Density 0.008%

No Known Activations

This feature has no known activations.