INDEX

Explanations

names and dignity

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

 unordered

-0.28

+r

-0.28

æĻ®

-0.26

ipt

-0.26

 Furn

-0.26

ä¸ºä¹ĭ

-0.25

çľĭå¾Ĺ

-0.25

-columns

-0.25

åĩĨ

-0.24

ä¹ĥ

-0.24

POSITIVE LOGITS

dbo

0.31

ÑĨÐ¸ÑĤ

0.27

oton

0.27

AdapterManager

0.26

LocalizedString

0.25

\|

0.25

Pooling

0.24

 chatter

0.24

ÑģÑı

0.24

è£ģ

0.23

Activations Density 0.001%

names and dignity

No Comments

No Known Activations