INDEX

Explanations

emphasis, focus in writing

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

POD

-0.27

Spoiler

-0.26

 Moderator

-0.25

esar

-0.25

éĽĦåİļ

-0.24

MethodInfo

-0.24

Ctrls

-0.24

cce

-0.23

/change

-0.23

Cyr

-0.23

POSITIVE LOGITS

å°ģ

0.26

è¿ĻæĿ¡

0.26

åĪ¤

0.26

ç»ıéªĮ

0.26

ature

0.26

atal

0.26

attr

0.26

opause

0.25

 efforts

0.25

atters

0.24

Activations Density 13.764%

emphasis, focus in writing

No Comments

No Known Activations