INDEX

Explanations

laboratory

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

pref

-0.28

false

-0.28

clerosis

-0.27

æĻļ

-0.26

æĢª

-0.25

æİ¥è¿ŀ

-0.25

 approach

-0.25

 paths

-0.25

 false

-0.24

è´´

-0.24

POSITIVE LOGITS

æ¡·

0.29

iever

0.29

 Ð¿Ñĥ

0.27

ç¯Ŀ

0.26

ieved

0.26

KIT

0.25

ettle

0.25

æ²¸

0.24

quila

0.24

["@

0.24

Activations Density 0.003%

laboratory

No Comments

No Known Activations