INDEX

Explanations

on

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

 prive

-0.27

å°ıå¹ħ

-0.26

 puls

-0.26

bi

-0.26

 refl

-0.25

åĮĸçŁ³

-0.25

æŃĻ

-0.25

du

-0.25

ax

-0.25

PS

-0.24

POSITIVE LOGITS

 Ordering

0.25

idores

0.25

 getOrder

0.25

.eof

0.24

anian

0.24

åľ°æĿ¿

0.24

GetProperty

0.23

zij

0.23

å¤©æ²³

0.23

_Order

0.23

Activations Density 0.000%

on

No Comments

No Known Activations