INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

_Entry

-0.29

_ENTRY

-0.28

åĢ¡è®®

-0.27

åĩºçİ°

-0.26

åĪ°åľº

-0.25

inta

-0.25

 thats

-0.24

izz

-0.24

 anarch

-0.24

åĮį

-0.24

POSITIVE LOGITS

.Cos

0.28

atura

0.27

è±ª

0.26

æ¶¯

0.25

ardu

0.25

éģĤ

0.25

lando

0.25

POR

0.25

 Gros

0.24

ä¿Ŀ

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.