INDEX

Explanations

filler words and prepositions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

otta

-0.34

itta

-0.29

iring

-0.28

pra

-0.26

(QtGui

-0.25

è¶Ł

-0.25

wagon

-0.25

//<

-0.24

-sama

-0.24

undef

-0.24

POSITIVE LOGITS

æĢİ

0.52

 what

0.42

ä»Ģä¹Ī

0.42

 What

0.40

æĺ¯ä»Ģä¹Ī

0.39

ä»Ģéº¼

0.39

åĵªå®¶å¥½

0.38

åĵªç§į

0.38

æĢİæł·

0.38

ä»Ģä¹Īæł·çļĦ

0.38

Activations Density 0.016%

filler words and prepositions

No Comments

No Known Activations