INDEX

Explanations

understanding

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

ä¸ĩæĪ·

-0.32

å·´å£«

-0.26

 proxies

-0.26

 Maze

-0.25

çĬį

-0.25

inders

-0.25

onyms

-0.25

-Isl

-0.25

 Ð±Ð¸Ð»

-0.24

ril

-0.24

POSITIVE LOGITS

çĽ¸è§ģ

0.29

 dimension

0.29

ç²ķ

0.28

èĭ¹

0.27

è¿Ļä¸ªéĹ®é¢ĺ

0.26

aqu

0.26

 dimensional

0.25

Dimension

0.25

 Dimension

0.25

foreground

0.25

Activations Density 0.004%

understanding

No Comments

No Known Activations