INDEX

Explanations

golf

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

è¶Ĭæĺ¯

-0.31

æĿ¥æºĲ

-0.30

 ApplicationRecord

-0.29

è¶Ĭ

-0.28

 source

-0.27

source

-0.27

 ostream

-0.27

 sources

-0.27

 nameof

-0.25

æºĲ

-0.25

POSITIVE LOGITS

ett

0.26

 lovers

0.26

resident

0.25

rab

0.25

nut

0.24

æĢ»æĶ¶åħ¥

0.24

ulls

0.24

 dorm

0.23

åĿĩ

0.23

brains

0.23

Activations Density 0.038%

golf

No Comments

No Known Activations