INDEX

Explanations

aeronautics and aerospace

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

squ

-0.27

stry

-0.27

opsis

-0.27

antry

-0.25

iples

-0.25

Ãłi

-0.25

anse

-0.24

æĭŃ

-0.24

å¤ĩ

-0.24

ske

-0.24

POSITIVE LOGITS

ä¸Ĭè°ĥ

0.27

à¹Ģà¸¥à¸¢

0.27

é¸¾

0.25

iner

0.24

 downs

0.24

ropolis

0.24

 Returned

0.24

 Joined

0.24

ulance

0.24

ksz

0.23

Activations Density 0.008%

aeronautics and aerospace

No Comments

No Known Activations