INDEX

Explanations

addresses

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

 Covered

-0.29

çŁ¥éģĵèĩªå·±

-0.27

isque

-0.27

åºĶè¯¥æĺ¯

-0.26

.central

-0.26

bgcolor

-0.25

ero

-0.24

 onData

-0.24

Ã¥r

-0.24

isclosed

-0.24

POSITIVE LOGITS

option

0.30

 option

0.29

ption

0.28

stack

0.28

 Option

0.28

èĲİ

0.28

.Stack

0.27

 treason

0.26

Option

0.25

éĢīé¡¹

0.25

Activations Density 0.103%

addresses

No Comments

No Known Activations