INDEX

Explanations

micro

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĬµæĬĹåĬĽ

-0.29

-encoded

-0.28

ãĥ³ãĤ°

-0.26

 censor

-0.26

 Round

-0.25

éķ¿èĢģ

-0.24

-serif

-0.24

fers

-0.24

 impost

-0.24

 phÃ©

-0.24

POSITIVE LOGITS

ç¬ĳçĿĢ

0.28

awi

0.27

xBB

0.27

ApiClient

0.26

.sap

0.25

elle

0.25

/+

0.25

Ã©ra

0.25

'https

0.25

scopy

0.24

Activations Density 0.117%

micro

No Comments

No Known Activations