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

PT

-0.28

suf

-0.27

ï

-0.27

 Persian

-0.26

oes

-0.25

å¤§éĺŁ

-0.25

imps

-0.25

 ])->

-0.25

oz

-0.25

æµģæ°´

-0.25

POSITIVE LOGITS

çħ

0.28

é³³

0.25

scribe

0.24

åĻ¤

0.24

Bip

0.24

 forgiven

0.24

éļĶå£ģ

0.24

 Allocate

0.23

voke

0.23

 Frog

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.