INDEX

Explanations

various internet text snippets

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Sit

-0.28

sit

-0.27

 settle

-0.26

 settling

-0.25

pattern

-0.25

-layout

-0.25

Sit

-0.24

BY

-0.24

 zusammen

-0.24

arend

-0.23

POSITIVE LOGITS

Ð¸ÑĩÐµÑģÐºÐ¸Ð¹

0.30

strap

0.29

.fore

0.27

isÃ©

0.25

bro

0.25

Incre

0.24

 Compound

0.24

.Interop

0.23

imm

0.23

è°ķ

0.23

Activations Density 0.022%

various internet text snippets

No Comments

No Known Activations