INDEX

Explanations

must

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

åıįå¤į

-0.26

means

-0.25

åıį

-0.24

 Extras

-0.24

apo

-0.24

æĸĩæĺİ

-0.23

 Ø¢

-0.23

upp

-0.23

äºĳ

-0.23

å±ĭ

-0.23

POSITIVE LOGITS

 complementary

0.27

 meshes

0.26

ateurs

0.25

è¿Ļè¯Ŀ

0.25

äºĴè¡¥

0.24

thon

0.24

 elective

0.24

ilee

0.24

 Mesh

0.23

ä¾¦å¯Ł

0.23

Activations Density 0.112%

must

No Comments

No Known Activations