INDEX

Explanations

to

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

æĭ£

-0.26

é«ĺå³°æľŁ

-0.25

äººéĢī

-0.25

åħ¶ä¸Ńä¹ĭä¸Ģ

-0.25

moduleName

-0.25

["@

-0.25

uteur

-0.24

 Bannon

-0.24

é«ĺå³°

-0.24

 resourceName

-0.23

POSITIVE LOGITS

 math

0.29

Ap

0.27

 logical

0.26

å¤·

0.25

 vuel

0.25

Bod

0.25

tik

0.25

 slip

0.24

(math

0.24

crets

0.24

Activations Density 0.001%

to

No Comments

No Known Activations