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

å°±ä¸ļå²Ĺä½į

-0.28

 Crushers

-0.27

éĩįè¦ģåĽłç´ł

-0.27

 Rosenstein

-0.24

å®ŀä¹łçĶŁ

-0.24

][$

-0.24

é«ĺåĩº

-0.23

çİ¯å¢ĥæ±¡æŁĵ

-0.23

äº§åĢ¼

-0.23

âĢ¦↵↵↵↵

-0.23

POSITIVE LOGITS

æľīäººè¯´

0.30

gt

0.28

çĲĨ

0.27

day

0.27

æľīäºº

0.27

terr

0.26

vl

0.25

tl

0.25

cast

0.24

Day

0.24

Activations Density 0.018%

No Known Activations

This feature has no known activations.