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

uso

-0.28

anko

-0.26

è¯ķåīĤ

-0.25

uci

-0.25

lers

-0.25

ÃŃcio

-0.24

.DialogInterface

-0.24

ä½įç½®

-0.24

éĻĲ

-0.24

ini

-0.24

POSITIVE LOGITS

HasKey

0.25

Opr

0.25

:[[

0.24

å¼ºæľīåĬĽçļĦ

0.24

 Elastic

0.23

 uncomment

0.23

lobal

0.23

å·²ç»ıæľīäºĨ

0.23

å°Ĩè¿Ľä¸ĢæŃ¥

0.23

};↵↵↵↵

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.