INDEX

Explanations

choice, influence, control

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

ä¿¡å¿ĥ

-0.32

aine

-0.27

amide

-0.24

ä½łä¼ļåıĳçİ°

-0.24

çļĦä¿¡å¿ĥ

-0.24

å®ŀäºĭæ±Ĥ

-0.24

flamm

-0.24

usses

-0.23

Arduino

-0.23

ä¼ļè®©ä½ł

-0.23

POSITIVE LOGITS

å¦Ĥä½ķ

0.46

how

0.41

How

0.36

èĩªå·±çļĦ

0.35

æĢİä¹Ī

0.35

æĺ¯å¦Ĥä½ķ

0.34

å¦Ĥä½ķçľĭå¾ħ

0.31

posal

0.30

æĢİæł·

0.29

How

0.28

Activations Density 0.002%

choice, influence, control

No Comments

No Known Activations