INDEX

Explanations

food and health

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĺ¹

-0.28

inherits

-0.27

ailable

-0.26

 EITHER

-0.26

ottie

-0.25

ä¸įå¤±

-0.25

 coronavirus

-0.25

 stret

-0.25

 hers

-0.24

herits

-0.24

POSITIVE LOGITS

weise

0.28

.dt

0.27

cad

0.27

IDE

0.26

èģĶç³»æĸ¹å¼ı

0.25

IDE

0.25

yan

0.25

 Dahl

0.24

ye

0.24

rice

0.23

Activations Density 0.000%

food and health

No Comments

No Known Activations