INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 convey

-0.28

nite

-0.26

dig

-0.26

quets

-0.24

finite

-0.24

 .č↵

-0.24

 trÃŃ

-0.24

forcement

-0.23

æŀľ

-0.23

ä½Ļ

-0.23

POSITIVE LOGITS

uko

0.27

LAN

0.25

çģµæķı

0.25

à¹īà¸²à¸Ļ

0.24

accordion

0.24

åģļçļĦ

0.24

ä¸ªäººä¿¡æģ¯

0.24

itor

0.24

æķıæĦŁ

0.23

è¿Ļä¸ªè¯į

0.23

Activations Density 0.046%

No Known Activations

This feature has no known activations.