INDEX

Explanations

blowing

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 behold

-0.28

 fulfilling

-0.27

æĹĹ

-0.26

hor

-0.26

hor

-0.24

ä¸Ģåľº

-0.24

ä»¿

-0.24

 beach

-0.24

ecl

-0.24

-horizontal

-0.24

POSITIVE LOGITS

Ð·Ð¸

0.29

Mass

0.26

 stil

0.26

opal

0.24

fiz

0.24

olic

0.24

SizeMode

0.24

,copy

0.24

cole

0.24

.Expression

0.24

Activations Density 0.001%

blowing

No Comments

No Known Activations