INDEX

Explanations

AFP

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

é¡¹

-0.27

æľīåħ³

-0.25

eni

-0.25

.AttributeSet

-0.25

"$

-0.25

åĲĦæł·

-0.25

 Kore

-0.24

esen

-0.24

TERS

-0.24

vu

-0.23

POSITIVE LOGITS

olk

0.26

ascript

0.26

SVC

0.25

sie

0.24

äº¬

0.24

eid

0.24

ãĤ·ãĤ¢

0.24

Sie

0.24

matic

0.24

inders

0.24

Activations Density 8.038%

AFP

No Comments

No Known Activations