INDEX

Explanations

Random snippets of texts

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

 propensity

-0.29

OTO

-0.28

æ¡Ĩ

-0.27

OPLE

-0.27

åī§

-0.26

åı¯èĥ½åıĳçĶŁ

-0.26

ople

-0.26

OVE

-0.25

 trans

-0.24

ç¼ĸ

-0.24

POSITIVE LOGITS

edException

0.26

 Abbas

0.26

 StyleSheet

0.25

æĢİä¹Īåģļ

0.25

wers

0.25

avenport

0.25

è¿½èµ¶

0.25

å®ŀæĸ½ç»ĨåĪĻ

0.24

-upper

0.24

StyleSheet

0.24

Activations Density 0.005%

Random snippets of texts

No Comments

No Known Activations