INDEX

Explanations

technical/professional content

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĽĻåħī

-0.27

iple

-0.26

fragment

-0.25

éĿĴæĺ¥

-0.25

rox

-0.25

underscore

-0.25

 twilight

-0.25

riter

-0.25

teen

-0.24

åĲ¹

-0.24

POSITIVE LOGITS

orum

0.27

æĶ¶æĭ¾

0.25

iates

0.24

Bor

0.24

æİ¸

0.24

pio

0.24

 BuzzFeed

0.24

 inhab

0.24

éĿ©

0.24

Tar

0.24

Activations Density 0.008%

technical/professional content

No Comments

No Known Activations