INDEX

Explanations

uj

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

íĮ¨

-0.26

bour

-0.26

subjects

-0.25

ÑīÐ¸Ð½

-0.25

ivel

-0.24

iative

-0.24

ButtonType

-0.24

imuth

-0.24

irts

-0.24

egree

-0.24

POSITIVE LOGITS

-archive

0.26

.createQuery

0.25

.WriteString

0.25

cal

0.25

arch

0.24

ä»ĸæĺ¯

0.24

 kotlin

0.23

Archive

0.23

 archive

0.23

archive

0.23

Activations Density 48.246%

uj

No Comments

No Known Activations