INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

blind

-0.30

åĮĻ

-0.30

addListener

-0.30

ledge

-0.28

jar

-0.27

afs

-0.26

retch

-0.25

æĽ¿ä»£

-0.25

-blind

-0.24

['.

-0.24

POSITIVE LOGITS

.instructions

0.26

èĦĲ

0.26

uzu

0.26

bir

0.26

åĦ¿å¥³

0.25

çĶŁæ°Ķ

0.25

conds

0.24

çļĦäºĭæĥħ

0.24

AsyncResult

0.24

idebar

0.24

Activations Density 0.061%

No Known Activations

This feature has no known activations.