INDEX

Explanations

for

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æµģéĢļ

-0.26

 haci

-0.26

mina

-0.24

hint

-0.24

è§£åĨ³æĸ¹æ¡Ī

-0.24

ihan

-0.24

æ¼ı

-0.24

 flowing

-0.24

 Cree

-0.23

ISC

-0.23

POSITIVE LOGITS

ÅĦski

0.28

heimer

0.27

ries

0.27

rier

0.26

amel

0.25

ums

0.25

rou

0.25

riers

0.24

antan

0.24

 compounded

0.24

Activations Density 0.003%

for

No Comments

No Known Activations