INDEX

Explanations

commas

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å½ĵåīįä½įç½®

-0.31

Iv

-0.27

lood

-0.27

æ¤į

-0.25

.perm

-0.25

èĳ©

-0.25

 lifes

-0.24

.setLocation

-0.24

 inorder

-0.24

 actionPerformed

-0.24

POSITIVE LOGITS

å¢ĥ

0.29

æĥ³ä¸įåĪ°

0.28

isan

0.27

{$

0.26

ç®Ĺæĺ¯

0.26

ä¸Ģå¯¹

0.25

 myster

0.25

éĺĲ

0.25

åıĪ

0.24

è°ĥæŁ¥æĺ¾ç¤º

0.24

Activations Density 1.643%

commas

No Comments

No Known Activations