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

 nghi

-0.34

è¿Ļæĺ¯

-0.26

éĻ©

-0.26

æ´¥

-0.26

è¿Ĳæ²³

-0.25

è¯¾

-0.25

pageIndex

-0.24

çĻĮ

-0.24

æĮª

-0.24

 liá»ĩu

-0.24

POSITIVE LOGITS

 anthrop

0.29

eous

0.28

<!--↵

0.27

æİĴæĸ¥

0.27

ä¸»ç®¡

0.26

Ð²ÐµÑĩ

0.25

ECH

0.25

ilent

0.25

çģ«çĥ§

0.25

 Jewel

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.