INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ients

-0.30

ÙĪØ¨Ø©

-0.26

 getContent

-0.26

<ll

-0.25

ernen

-0.25

éĩįå¿ĥ

-0.25

tps

-0.23

çŁ¶

-0.23

ipel

-0.23

çĻ¯

-0.22

POSITIVE LOGITS

form

0.27

WORD

0.26

æĢ»éĺŁ

0.25

åĲįè¯į

0.24

 emitting

0.24

erro

0.24

atable

0.23

åı·çłģ

0.23

 Griff

0.22

glÄħd

0.22

Activations Density 0.140%

No Known Activations

This feature has no known activations.