INDEX

Explanations

email/online posts

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

ick

-0.27

 PATCH

-0.26

 gÃ¶

-0.25

Noise

-0.25

 Noise

-0.24

 chÃ³ng

-0.24

æĭ©

-0.24

æ°¸ä¸į

-0.24

unce

-0.23

è®¤çľŁåŃ¦ä¹ł

-0.23

POSITIVE LOGITS

mez

0.31

walker

0.29

ionale

0.28

¾ç¤º

0.28

[loc

0.27

enth

0.27

åĪ°ä½į

0.26

 sexes

0.26

dden

0.25

cene

0.25

Activations Density 1.664%

email/online posts

No Comments

No Known Activations