INDEX

Explanations

hydro

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anja

-0.28

åĳ¢

-0.28

 burnt

-0.27

åħ¨æ°ĳåģ¥èº«

-0.26

à¸²à¸ĩ

-0.26

æł·åŃĲ

-0.26

ä¸Ĭå®ĺ

-0.25

äºĨåĲ§

-0.25

 succ

-0.25

 TestData

-0.25

POSITIVE LOGITS

æīĵäº¤éģĵ

0.30

ennes

0.27

ugar

0.27

Growing

0.26

chants

0.26

è½¦åŀĭ

0.25

itle

0.25

åįļ

0.24

 Growing

0.24

acks

0.24

Activations Density 0.004%

hydro

No Comments

No Known Activations