INDEX

Explanations

privilege

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chs

-0.28

-gen

-0.26

 chunks

-0.26

oot

-0.26

åĮħè£¹

-0.25

plat

-0.25

 procur

-0.25

ismic

-0.25

åľ¨è¿Ļç§į

-0.25

ecture

-0.24

POSITIVE LOGITS

wed

0.28

 sacrific

0.28

 Demonstr

0.27

IBILITY

0.26

MENTS

0.26

æ¯Ķä¾ĭ

0.26

ä¸ģ

0.26

Demon

0.25

atisfied

0.24

ç±³ç²ī

0.24

Activations Density 0.007%

privilege

No Comments

No Known Activations