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

æĲĢ

-0.30

ectar

-0.30

Ä°L

-0.27

å§Ĳå¦¹

-0.27

ogs

-0.25

converter

-0.25

 converter

-0.24

vasion

-0.24

ä¸¤åı¥

-0.24

ospital

-0.24

POSITIVE LOGITS

.pth

0.25

vi

0.25

 masters

0.25

epy

0.25

 thÃ¹

0.25

ean

0.25

çħ¨

0.24

HttpException

0.24

BASEPATH

0.24

 enough

0.24

Activations Density 0.004%

No Known Activations

This feature has no known activations.