INDEX

Explanations

impact, influence, effect

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_10.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.10.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.basicConfig

-0.28

 WithEvents

-0.25

Ä±lÄ±r

-0.24

ÑħÐ¾Ð´Ð¸Ð¼

-0.24

åıĳçĶŁåľ¨

-0.24

 redirected

-0.24

 hors

-0.23

åľ¨è¿ĩæ¸¡

-0.23

ÅĤÄħ

-0.23

ä»¶äºĭ

-0.23

POSITIVE LOGITS

 Sheet

0.31

zet

0.28

iquer

0.27

zell

0.27

Ð»Ð¸

0.26

 Aval

0.26

 Poly

0.25

iers

0.25

lish

0.25

çªģ

0.25

Activations Density 0.001%

impact, influence, effect

No Comments

No Known Activations