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

edBy

-0.28

è¾Ī

-0.28

æķĳçģ¾

-0.27

è´¿

-0.27

ajar

-0.26

bare

-0.26

ARB

-0.25

ResultsController

-0.25

BW

-0.24

åįĥéĩĮ

-0.24

POSITIVE LOGITS

ensity

0.29

akedown

0.29

éĿ¢çĻ½

0.27

rose

0.26

 prior

0.25

ct

0.25

åĿĽ

0.25

che

0.24

 compensation

0.24

CORD

0.23

Activations Density 0.014%

No Known Activations

This feature has no known activations.