INDEX

Explanations

J

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èį·åħ°

-0.31

èį·

-0.30

alen

-0.29

abbo

-0.27

orld

-0.26

scenario

-0.26

rand

-0.26

okie

-0.25

 Netherlands

-0.25

emens

-0.25

POSITIVE LOGITS

ion

0.30

_requires

0.27

iones

0.26

ç½ĳé¦ĸé¡µ

0.25

sm

0.25

ione

0.25

ByPrimaryKey

0.24

 Smith

0.24

æ»¡

0.24

ionic

0.23

Activations Density 0.003%

J

No Comments

No Known Activations