INDEX

Explanations

software errors or code questions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ah

-0.29

potential

-0.27

éĿĴå±±

-0.25

AH

-0.25

andering

-0.24

æĭ¿åĪ°

-0.24

 Accessed

-0.24

Kah

-0.24

 accessed

-0.24

Gig

-0.23

POSITIVE LOGITS

 appear

0.31

 dziaÅĤa

0.30

 works

0.29

 appears

0.28

 disappearing

0.27

åĩºçİ°

0.27

rompt

0.27

 Ð´Ð¾Ð»Ð»

0.27

 ÑĢÐ°Ð±Ð¾ÑĤÐ°ÐµÑĤ

0.26

 ÑģÐ»Ð¸

0.26

Activations Density 0.028%

software errors or code questions

No Comments

No Known Activations