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

 chilled

-0.27

TeV

-0.25

 originals

-0.25

ersed

-0.24

azing

-0.24

yled

-0.24

unset

-0.24

èĥĿ

-0.24

oref

-0.23

ä¸ºåħ¶

-0.23

POSITIVE LOGITS

å³ģ

0.25

 favourites

0.25

 KaÅ¼dy

0.25

lio

0.25

æĲº

0.24

é¡¿

0.24

Ã¢n

0.23

èĪĨ

0.23

 favourite

0.23

ubi

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.