INDEX

Explanations

dashes

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

oyo

-0.27

imen

-0.26

åĨĻéģĵ

-0.25

ä»įå°Ĩ

-0.25

éĺĸ

-0.24

é©¬æĭī

-0.24

æĪĳåıĳçİ°

-0.24

OOT

-0.24

claimer

-0.24

isoft

-0.24

POSITIVE LOGITS

 Zombies

0.27

ĥģ

0.26

æ¶Īè´¹

0.26

ln

0.25

ln

0.25

ÑĢÐµÑģÑĤ

0.24

abs

0.24

 há»Ļi

0.23

é¹ĺ

0.23

stered

0.23

Activations Density 0.083%

dashes

No Comments

No Known Activations