INDEX

Explanations

following a lead/example

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

åİ³ãģĹãģĦ

-0.27

bib

-0.26

("@

-0.26

è½¬è½½è¯·

-0.26

 Heritage

-0.25

è¯Ĺäºº

-0.25

-vs

-0.24

æľīæľº

-0.23

"@

-0.23

 Pocket

-0.23

POSITIVE LOGITS

inde

0.37

 compte

0.29

certificate

0.27

 Borders

0.27

angle

0.27

ilton

0.27

ç»ĪçĶŁ

0.27

 Deutsch

0.26

 Certificate

0.26

 certificate

0.26

Activations Density 0.035%

following a lead/example

No Comments

No Known Activations