INDEX

Explanations

income

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

BCH

-0.25

ceries

-0.25

erton

-0.25

 Fitness

-0.25

æł¸æŁ¥

-0.24

 exceptions

-0.24

ä¹ĭåŁİ

-0.24

 Flower

-0.24

orts

-0.24

exceptions

-0.24

POSITIVE LOGITS

xFE

0.29

ikip

0.27

xfe

0.27

loon

0.26

sam

0.26

:message

0.26

 Hast

0.25

è¿Ļä¸īä¸ª

0.25

press

0.25

èĩ´

0.25

Activations Density 0.050%

income

No Comments

No Known Activations