INDEX

Explanations

online posts

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

 surtout

-0.28

á»Ŀ

-0.27

æķĳæĬ¤

-0.26

ä»Ģä¹Īåĳ¢

-0.26

lege

-0.25

åĲįèªī

-0.24

 Contributors

-0.24

 cycling

-0.24

çĶ¨æĪ·åĲį

-0.24

 epochs

-0.24

POSITIVE LOGITS

è±Ĩ

0.30

 Paste

0.29

 paste

0.27

dao

0.26

graf

0.26

ãģªãģ®ãģ«

0.25

Generated

0.25

 ordin

0.25

 powsta

0.25

createFrom

0.24

Activations Density 0.007%

online posts

No Comments

No Known Activations