INDEX

Explanations

cycle

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

Wake

-0.31

 Wake

-0.29

arks

-0.29

 bergen

-0.28

.gs

-0.28

alytics

-0.27

abouts

-0.27

yro

-0.26

race

-0.25

vla

-0.25

POSITIVE LOGITS

dr

0.32

dd

0.28

 reserv

0.26

ä¸ŃåįİæĸĩåĮĸ

0.26

...

0.26

 manual

0.25

çĽ®æłĩ

0.25

 reserved

0.25

 subscript

0.25

 addressed

0.25

Activations Density 0.001%

cycle

No Comments

No Known Activations