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

iets

-0.26

eus

-0.24

mentor

-0.24

èĩ³åħ³

-0.24

_DM

-0.24

 loaf

-0.24

 ---↵

-0.24

ecz

-0.24

rale

-0.24

Ð¶Ð¸ÑĤÑĮ

-0.24

POSITIVE LOGITS

te

0.28

 understands

0.27

 realizes

0.27

 chai

0.27

urt

0.25

min

0.25

æĶ¶è´¹æłĩåĩĨ

0.25

ä¸Ĭåįĩ

0.25

te

0.25

æ£Ģæµĭ

0.25

Activations Density 0.015%

No Known Activations

This feature has no known activations.