INDEX

Explanations

olympia

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

 Tmin

-0.33

Bog

-0.29

â½Ģ

-0.26

æ¯³

-0.26

Porn

-0.25

NIL

-0.25

 InitializeComponent

-0.25

edList

-0.24

tog

-0.24

è¿ĻæĶ¯

-0.24

POSITIVE LOGITS

å¢ĥåĨħ

0.31

avar

0.28

ines

0.28

çµ

0.27

cor

0.27

åĥı

0.26

 flattened

0.26

 flat

0.26

over

0.25

flat

0.25

Activations Density 0.002%

olympia

No Comments

No Known Activations