INDEX

Explanations

code

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

ãĥĵãĤ¸

-0.30

 Hearts

-0.27

ä¸ĸå®¶

-0.26

front

-0.26

èĥ½åĬĽ

-0.26

 multit

-0.25

XCT

-0.25

adies

-0.25

URT

-0.25

ç§¯

-0.24

POSITIVE LOGITS

uche

0.30

["@

0.28

downloads

0.26

ç³Ļ

0.25

zik

0.25

#{@

0.25

arel

0.24

æŁ¥çľĭåħ¨æĸĩ

0.24

è¯»åĲİ

0.24

æı´

0.24

Activations Density 0.019%

code

No Comments

No Known Activations