INDEX

Explanations

medicine and orthopedics

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

 conc

-0.28

å®¹

-0.27

act

-0.27

 conver

-0.27

incinnati

-0.26

acts

-0.26

ä»¿ä½Ľ

-0.26

iskey

-0.25

epend

-0.25

 complex

-0.25

POSITIVE LOGITS

reader

0.29

@js

0.28

->{'

0.26

ä¸Ľä¹¦

0.26

..↵↵↵↵

0.26

 SOUND

0.25

@qq

0.24

åĲ¬ä¼Ĺ

0.24

åĮºåĿĹ

0.24

,{"

0.24

Activations Density 0.266%

medicine and orthopedics

No Comments

No Known Activations