INDEX

Explanations

math equations

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

-cell

-0.28

 Cell

-0.26

liv

-0.25

 consumed

-0.25

 cell

-0.25

è®¤çľŁ

-0.25

yun

-0.24

istique

-0.24

usta

-0.24

asis

-0.24

POSITIVE LOGITS

Mot

0.26

sal

0.25

æ±Łæ¹ĸ

0.24

éĻ¢éĻ¢éķ¿

0.24

æīį

0.24

Ã¼lt

0.24

/me

0.24

æĸĩ

0.24

odeled

0.24

few

0.23

Activations Density 0.066%

math equations

No Comments

No Known Activations