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

 posix

-0.26

igg

-0.25

hoe

-0.24

Finder

-0.24

åıĳå±ķä¸Ń

-0.24

folio

-0.24

raphics

-0.24

ToFront

-0.23

rob

-0.23

ãģŀ

-0.23

POSITIVE LOGITS

lite

0.28

otal

0.26

è½¸

0.24

ä¹ĭæīĢ

0.24

lemn

0.24

lane

0.24

 eigen

0.23

æ¡¢

0.23

atrix

0.23

[,]

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.