INDEX

Explanations

airing

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

redit

-0.28

')}}↵

-0.27

FIL

-0.27

Fil

-0.26

gere

-0.25

])))

-0.25

afort

-0.25

 sounds

-0.25

%'↵

-0.25

 realistically

-0.25

POSITIVE LOGITS

 fare

0.27

æ±Ĥ

0.26

ä¼ª

0.26

 tissues

0.26

.API

0.26

è£ħæī®

0.25

æĢĢæĬ±

0.24

æ²¿éĢĶ

0.24

å¸ĥç½®

0.24

bip

0.23

Activations Density 0.004%

airing

No Comments

No Known Activations