INDEX

Explanations

become

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Crime

-0.29

Ð¾ÑģÑĤÑĮÑİ

-0.29

nil

-0.27

ilege

-0.26

ideon

-0.25

 Become

-0.25

Suk

-0.25

(po

-0.25

è¸©

-0.24

éºŁ

-0.24

POSITIVE LOGITS

 rather

0.42

 into

0.38

rather

0.37

 known

0.37

 possible

0.36

 feasible

0.35

 plutÃ´t

0.33

into

0.32

_into

0.32

Into

0.32

Activations Density 0.025%

become

No Comments

No Known Activations