INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

"@"

-0.26

DJs

-0.26

 doubt

-0.26

-enable

-0.25

discount

-0.24

æľĢä¼ĺ

-0.24

 enim

-0.24

/exec

-0.24

gL

-0.23

["@

-0.23

POSITIVE LOGITS

æ¡¥

0.27

åİĨåı²æĸĩåĮĸ

0.25

åĴı

0.25

çĽ¸åħ³åĨħå®¹

0.25

_FRONT

0.25

ub

0.24

inge

0.24

åĨ²

0.24

ç»Ļå¥¹

0.24

Ub

0.24

Activations Density 14.450%

No Known Activations

This feature has no known activations.