INDEX

Explanations

online communication and dating

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Vk

-0.28

lander

-0.27

 Herald

-0.27

sez

-0.26

gars

-0.26

ç§¯ç´¯

-0.25

æį¢

-0.25

ä¸Ģæĸ¹

-0.25

mens

-0.25

alf

-0.24

POSITIVE LOGITS

å¿ĥèĦıçĹħ

0.30

İĺìĿ´

0.27

rote

0.26

 enlarged

0.26

åĹ¡

0.26

 confidential

0.26

_slow

0.25

.EVT

0.25

 Ð¿Ð¾Ð²ÑĭÑĪÐµÐ½

0.25

addOn

0.25

Activations Density 0.001%

online communication and dating

No Comments

No Known Activations