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

dorf

-0.32

urf

-0.29

æ¦Ĥå¿µ

-0.27

ç«ŁçĦ¶

-0.26

EDIA

-0.26

itics

-0.26

 Antony

-0.25

tte

-0.25

æĪĲäºĨ

-0.25

æ²¡æ³ķ

-0.25

POSITIVE LOGITS

File

0.29

 drawn

0.27

æĵĺ

0.25

reck

0.24

åĽłä¸ºå¥¹

0.24

/UI

0.23

æĬ½åĩº

0.23

.Draw

0.23

 excell

0.23

ken

0.23

Activations Density 0.815%

No Known Activations

This feature has no known activations.