INDEX

Explanations

pain

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

æĸ½å·¥çİ°åľº

-0.27

BOX

-0.25

ç²īæľ«

-0.25

_combine

-0.25

diamond

-0.23

build

-0.23

protocol

-0.23

 onBind

-0.23

 REPL

-0.23

 truth

-0.23

POSITIVE LOGITS

Ã¥n

0.34

elps

0.27

 SLOT

0.26

æ§½

0.25

èĬĭ

0.25

iline

0.25

åıĳä½ľ

0.25

olars

0.25

æ´±

0.24

ADS

0.24

Activations Density 0.002%

pain

No Comments

No Known Activations