INDEX

Explanations

technical/informational content

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

atos

-0.29

utow

-0.29

ariat

-0.27

 legend

-0.26

å¯Ħæīĺ

-0.25

æ¯ıå¹´éĥ½

-0.24

irse

-0.24

ãģ©ãģĵãĤį

-0.24

rad

-0.24

RAD

-0.24

POSITIVE LOGITS

deg

0.29

 cred

0.26

æĭŁ

0.26

ä¸´

0.25

*num

0.25

cred

0.25

å½¢å®¹

0.25

deb

0.25

.uniform

0.24

rig

0.24

Activations Density 0.002%

technical/informational content

No Comments

No Known Activations