INDEX

Explanations

code and documentation

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

.getProperty

-0.28

 GUIDE

-0.28

 guide

-0.27

fic

-0.27

 handbook

-0.26

Css

-0.26

_OPCODE

-0.26

 instructions

-0.26

 guides

-0.25

,"

-0.25

POSITIVE LOGITS

æĪĳè¯´

0.27

å¥½è¯Ħ

0.26

åĲĪ

0.26

æ²»æĦĪ

0.26

å¥½äºĭ

0.26

ego

0.26

borg

0.26

ç®Ģæ´ģ

0.25

ä¾¿

0.25

colon

0.25

Activations Density 5.752%

code and documentation

No Comments

No Known Activations