INDEX

Explanations

railway

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

 horizontally

-0.28

 forecast

-0.27

ynet

-0.26

bum

-0.25

æĪ¿å±ĭ

-0.25

ÙĥÙĩ

-0.24

å¤©åľ°

-0.24

>>)

-0.24

-figure

-0.24

ªĮ

-0.24

POSITIVE LOGITS

çľ¼çļ®

0.31

èĩªæĿ¥

0.29

éħ¬

0.28

MZ

0.26

hart

0.26

å¼Ħ

0.26

 ÅŁ

0.25

è´¹

0.25

ais

0.25

ais

0.25

Activations Density 0.122%

railway

No Comments

No Known Activations