INDEX

Explanations

to

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

gio

-0.30

beits

-0.27

ainment

-0.26

eref

-0.26

Crop

-0.25

thÃ¨que

-0.25

ä¹°åĪ°

-0.24

confirmation

-0.24

 confirmation

-0.23

_ASSOC

-0.23

POSITIVE LOGITS

 under

0.32

çİ¯

0.26

ç¼

0.26

å®¸

0.24

endum

0.24

maktadÄ±r

0.24

åıī

0.24

çĴ°

0.23

åĳ

0.23

tract

0.23

Activations Density 0.004%

to

No Comments

No Known Activations