INDEX

Explanations

programming code

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

uffs

-0.30

oro

-0.27

åĨįä¹Łæ²¡æľī

-0.27

osterone

-0.26

éĿ¢ç²ī

-0.26

_SUPPORTED

-0.25

 lÃ¦

-0.25

vez

-0.24

ä¸Ģåı£æ°Ķ

-0.24

uffy

-0.24

POSITIVE LOGITS

ä½įç½®

0.61

çļĦä½įç½®

0.60

 positions

0.54

 position

0.53

position

0.52

 location

0.50

 Position

0.48

 positioned

0.47

åľ°çĤ¹

0.47

 locations

0.45

Activations Density 0.010%

programming code

No Comments

No Known Activations