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

ä¼ĺèī¯

-0.28

éª¡

-0.27

 prominence

-0.25

 maxim

-0.25

 hern

-0.24

è´¸

-0.24

wcs

-0.24

orf

-0.24

èī¯

-0.24

 prosper

-0.23

POSITIVE LOGITS

ialis

0.33

iais

0.29

antly

0.27

noinspection

0.27

ctor

0.27

rial

0.27

ì¹ĺ

0.27

ILLA

0.26

åĬŀ

0.25

orial

0.25

Activations Density 0.796%

No Known Activations

This feature has no known activations.