INDEX

Explanations

check

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

mus

-0.30

ingles

-0.28

medi

-0.26

afs

-0.26

è²ĺ

-0.26

mus

-0.25

orsi

-0.25

ennis

-0.25

ä¸Ĳ

-0.25

want

-0.25

POSITIVE LOGITS

åĴĮä¸ªäºº

0.32

èĥ´

0.28

ä¸Ģçľĭ

0.28

 isValid

0.27

éĺ´

0.26

_principal

0.26

actory

0.26

noch

0.26

 isSuccess

0.25

ä¸ĢæĬ¹

0.25

Activations Density 0.049%

check

No Comments

No Known Activations