INDEX

Explanations

Code and technical discussions

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CS

-0.25

NAS

-0.25

æļ®

-0.25

rÃŃ

-0.25

æ³ģ

-0.24

Imm

-0.24

 trif

-0.24

 ÑĥÐ´Ð°Ð»

-0.24

lig

-0.23

å°ıç¼ĸ

-0.23

POSITIVE LOGITS

 atrÃ¡s

0.27

åĴĮå¹³

0.27

ono

0.27

missive

0.26

mas

0.25

unicorn

0.24

ties

0.24

sey

0.24

scalar

0.24

æĬ¼

0.24

Activations Density 0.113%

Code and technical discussions

No Comments

No Known Activations