INDEX

Explanations

colors

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä½ľåĵģåĨħå®¹

-0.28

æ¼ı

-0.28

 sinus

-0.26

æ±Ľ

-0.26

 bound

-0.25

æĪį

-0.25

å®¤åĨħ

-0.24

âĬ£

-0.24

 stabilized

-0.24

åĲĮæľŁ

-0.24

POSITIVE LOGITS

ILES

0.28

itaire

0.26

ListModel

0.25

æī©æķ£

0.24

uales

0.24

ä¹łæĥ¯

0.24

 Drivers

0.23

ickers

0.23

 Matte

0.23

 Paolo

0.23

Activations Density 0.004%

colors

No Comments

No Known Activations