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

atego

-0.27

+:

-0.27

 absence

-0.24

 Schw

-0.24

 Swift

-0.24

å®¡

-0.24

:?

-0.23

 weakened

-0.23

SWEP

-0.23

 combination

-0.23

POSITIVE LOGITS

ddf

0.26

'*

0.26

acas

0.26

æ°Ķè´¨

0.24

came

0.24

ç½®æį¢

0.24

terraform

0.24

ocument

0.24

dle

0.24

elter

0.24

Activations Density 0.011%

No Known Activations

This feature has no known activations.