INDEX

Explanations

these

np_max-act · gemini-2.0-flash

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

è¿ĻäºĽéĹ®é¢ĺ

-0.28

è¿Ļåĩł

-0.27

FolderPath

-0.26

esch

-0.26

oke

-0.25

à°³

-0.25

folder

-0.24

erd

-0.24

è¿ĻäºĽéĥ½æĺ¯

-0.24

Account

-0.24

POSITIVE LOGITS

ogens

0.30

ProgressHUD

0.27

çľ©

0.27

å°±æĺ¯åľ¨

0.26

agens

0.25

é«ĵ

0.24

å°±ä¸į

0.24

(QtGui

0.23

tres

0.23

ancement

0.23

Activations Density 0.016%

these

No Comments

No Known Activations