INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çĶŁäº§ç»ıèĲ¥

-0.26

éªİ

-0.25

sez

-0.25

ins

-0.24

 viet

-0.24

zie

-0.23

 tats

-0.23

UIS

-0.23

lood

-0.23

alic

-0.23

POSITIVE LOGITS

cape

0.29

åłķ

0.24

èĲ

0.23

å°¼

0.23

apse

0.23

ÐµÐ½Ð´

0.23

 ****************************************************************************

0.23

 nowhere

0.23

[^

0.23

 Weekly

0.23

Activations Density 0.611%

No Known Activations

This feature has no known activations.