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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¦ģå®³

-0.32

æĭĬ

-0.32

kie

-0.27

éĩĩ

-0.26

nak

-0.26

/books

-0.26

ki

-0.25

 habit

-0.25

PERT

-0.25

ime

-0.25

POSITIVE LOGITS

 chÃŃ

0.32

åľĴ

0.28

åĽŃ

0.28

.fi

0.27

gregate

0.27

Â´t

0.27

egr

0.26

âľ§

0.25

erner

0.25

lemn

0.25

Activations Density 0.155%

No Known Activations

This feature has no known activations.