INDEX

Explanations

research studies, data

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Å¥

-0.34

les

-0.26

 offend

-0.26

æĶ¯éĺŁ

-0.26

ayar

-0.26

åħ¬å¹³

-0.25

imen

-0.24

opath

-0.24

imens

-0.24

 Pied

-0.24

POSITIVE LOGITS

[end

0.29

,:)

0.28

 Everywhere

0.27

 Plenty

0.27

{j

0.26

 Mana

0.25

è¿ŀèĥľ

0.25

ìłģìĿ´

0.25

 mojo

0.25

âĨĹ

0.25

Activations Density 16.007%

research studies, data

No Comments

No Known Activations