INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 cent

-0.30

qu

-0.29

 design

-0.28

-wh

-0.27

 inter

-0.27

 whit

-0.26

 catch

-0.26

 provision

-0.26

 resist

-0.26

POSITIVE LOGITS

éļ¾æ°ĳ

0.29

 Worse

0.26

 neighbouring

0.25

 Credentials

0.25

å¤§å®Ĺ

0.24

 Spacer

0.24

 Sized

0.24

zsche

0.24

recipient

0.24

 Theft

0.24

Activations Density 0.018%

No Known Activations

This feature has no known activations.