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

æĬµæĬĹåĬĽ

-0.30

Parts

-0.29

***↵

-0.28

 oppon

-0.28

\Mail

-0.27

çŃīåĪ°

-0.27

å¼¥è¡¥

-0.25

inine

-0.25

å®¶äºº

-0.24

 Priv

-0.24

POSITIVE LOGITS

 winters

0.29

çİº

0.27

 Winter

0.27

 winter

0.26

 spokesperson

0.25

Ø¯Øª

0.25

Ð¸Ð³

0.24

ĸī

0.24

 scroll

0.24

rowse

0.23

Activations Density 0.064%

No Known Activations

This feature has no known activations.