INDEX

Explanations

Numbers and punctuation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

–and

-0.29

/from

-0.27

-volume

-0.27

âģĦ

-0.26

/j

-0.26

ãĢħ

-0.26

/OR

-0.26

å®«

-0.26

âĢ¦and

-0.25

/or

-0.25

POSITIVE LOGITS

###

0.27

æĽĿ

0.27

 Ð¿ÑĢÐ¸Ð½Ð¸Ð¼Ð°

0.25

 carve

0.25

yers

0.25

æ·±å±Ĥ

0.24

ç¼Ķ

0.24

æĭ±

0.23

ä¸Ģåı£

0.23

()

0.23

Activations Density 0.024%

Numbers and punctuation

No Comments

No Known Activations