INDEX

Explanations

of

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

è¯®

-0.27

ahkan

-0.27

atism

-0.27

YNAM

-0.26

propri

-0.26

 relic

-0.25

éħĴä¸ļ

-0.25

 stos

-0.25

 discredit

-0.25

èī¨

-0.25

POSITIVE LOGITS

oward

0.29

åĪ·æĸ°

0.27

æī¿è®¤

0.27

 Helping

0.26

èŃ¦

0.26

MIT

0.25

 indicators

0.24

ä¸»æĮģäºº

0.24

 limits

0.24

Activations Density 0.003%

of

No Comments

No Known Activations