INDEX

Explanations

and

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Drugs

-0.27

Contents

-0.26

 REALLY

-0.25

 radically

-0.25

 Prostit

-0.25

 Basics

-0.24

 useless

-0.24

 conceivable

-0.24

 greatly

-0.24

 someday

-0.24

POSITIVE LOGITS

getOption

0.28

é»ĺå¥ĳ

0.25

ĪæĿĥ

0.25

ãģ©

0.25

>(),↵

0.25

èĲ½åĪ°å®ŀ

0.24

å¯¼èĪª

0.24

 '/',

0.23

__),

0.23

çī¹æ´¾åĳĺ

0.23

Activations Density 1.035%

and

No Comments

No Known Activations