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

å©ī

-0.27

cient

-0.25

å¨´

-0.25

 chic

-0.25

æĭĴ

-0.24

 auto

-0.24

Ð¼ÐµÐ»

-0.23

è¯Ŀè¯Ń

-0.23

éģĳ

-0.23

unique

-0.23

POSITIVE LOGITS

ldr

0.27

MinMax

0.26

cratch

0.25

ä¸įä¸ĭ

0.25

 sectors

0.25

ä¹Łä¼ļ

0.25

è¿Ļæ®µ

0.24

æĪĳä»¬ä¹Ł

0.24

ä¹Łæĺ¯å¦ĤæŃ¤

0.24

 thems

0.24

Activations Density 0.009%

No Known Activations

This feature has no known activations.