INDEX

Explanations

on

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

bez

-0.30

cors

-0.28

 arch

-0.27

ven

-0.26

 appart

-0.25

æĹłçĸĳ

-0.25

 intrusion

-0.25

ä¸Ģä½ĵ

-0.25

Ø¬Ø¨

-0.25

 Ø§ÙĪ

-0.25

POSITIVE LOGITS

olics

0.28

-AA

0.26

ï¼ĮãĢĬ

0.25

åıªå¾Ĺ

0.23

(CG

0.23

 Ð¿ÑĢÐ¾Ð¸Ð·Ð²ÐµÐ´ÐµÐ½

0.23

 stresses

0.23

(dy

0.23

FromString

0.23

<Option

0.23

Activations Density 0.001%

on

No Comments

No Known Activations