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

ItemClick

-0.27

éķ¿å®ī

-0.27

POSIT

-0.27

ynchronize

-0.26

orners

-0.26

 graphical

-0.26

arel

-0.25

aways

-0.25

imson

-0.25

aret

-0.24

POSITIVE LOGITS

ä¹Ĳ

0.28

åĪĿæ¬¡

0.27

éĩĮ

0.27

ELY

0.27

æ¸Ĳ

0.26

éĢĲæ¸Ĳ

0.26

äº«åıĹ

0.26

æīĵçĿĢ

0.26

dragon

0.26

uro

0.26

Activations Density 0.000%

No Known Activations

This feature has no known activations.