INDEX

Explanations

to

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

ÐµÐ½Ð¸

-0.28

ndl

-0.26

.pat

-0.26

Fld

-0.26

æľīå¿ħè¦ģ

-0.25

ç²¾åįİ

-0.25

æķ·

-0.25

.getSelection

-0.24

iasi

-0.24

 bronze

-0.24

POSITIVE LOGITS

lette

0.29

istributed

0.28

LETTE

0.25

æĺº

0.25

çİ¯å¢ĥä¸ĭ

0.25

 eliminated

0.25

URY

0.25

æĿĳéķĩ

0.24

è¿Ĳè½¬

0.23

ocumented

0.23

Activations Density 0.001%

to

No Comments

No Known Activations