INDEX

Explanations

standards

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nis

-0.28

uish

-0.26

 ÑĤÐµÐº

-0.25

æİ¥è¿ĩ

-0.25

iams

-0.24

çķª

-0.24

ulla

-0.23

mur

-0.23

 condu

-0.23

-scroll

-0.23

POSITIVE LOGITS

(pad

0.27

 Ethiopian

0.25

 REQUIRED

0.24

angan

0.24

 Orthodox

0.24

ensch

0.24

 Gabri

0.23

igh

0.23

åħ»èĤ²

0.23

Activations Density 4.769%

standards

No Comments

No Known Activations