INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uts

-0.30

<?,

-0.25

MBER

-0.25

Props

-0.25

IDD

-0.24

*}

-0.24

FormField

-0.24

 Props

-0.23

*Math

-0.23

 Watches

-0.23

POSITIVE LOGITS

argc

0.29

arg

0.29

Arg

0.29

 argc

0.27

raith

0.27

_arg

0.27

LEN

0.27

arty

0.27

 argue

0.26

arg

0.25

Activations Density 23.384%

No Known Activations

This feature has no known activations.