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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

/format

-0.29

éĿ´

-0.28

æĪ´ä¸Ĭ

-0.28

å®īæħ°

-0.27

Bootstrap

-0.27

.hl

-0.26

otas

-0.26

orf

-0.26

çĮ©

-0.25

.SetValue

-0.25

POSITIVE LOGITS

 Railroad

0.26

nÃ¼

0.25

aden

0.24

ulu

0.24

ØªÙĪØ²

0.24

éĩĮç¨ĭ

0.23

.jupiter

0.23

 Rational

0.23

åŃĺåľ¨çļĦ

0.23

tad

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.