INDEX

Explanations

language

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uit

-0.29

ä¸Ĭå²Ĺ

-0.28

UIT

-0.26

åĲĮåŁİ

-0.26

Ã³n

-0.26

è´¶

-0.26

ault

-0.25

FD

-0.25

çŃīå¥ĸ

-0.25

File

-0.24

POSITIVE LOGITS

hort

0.27

ä¸ĢåĪĻ

0.26

æľĽ

0.26

 textDecoration

0.25

ä¸įåİ»

0.25

é«¡

0.25

lus

0.25

 recalled

0.24

uations

0.24

owns

0.24

Activations Density 0.159%

language

No Comments

No Known Activations