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

èŀį

-0.30

cy

-0.27

ä½ĵ

-0.27

æŁĵ

-0.27

erge

-0.27

ore

-0.26

 stro

-0.26

afs

-0.26

abor

-0.25

 elast

-0.25

POSITIVE LOGITS

æ§İ

0.27

ç³Ļ

0.27

FML

0.27

ç²²

0.26

çģ«èĬ±

0.26

itable

0.25

rical

0.25

'](

0.25

pecting

0.25

atical

0.25

Activations Density 0.005%

No Known Activations

This feature has no known activations.