INDEX

Explanations

.

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

UMB

-0.26

 formal

-0.26

stride

-0.25

ä»¬éĥ½

-0.25

imple

-0.25

 tween

-0.24

å¤ªå¹³

-0.24

thr

-0.24

 mend

-0.24

 embarrass

-0.23

POSITIVE LOGITS

dana

0.30

ÐµÐ»Ðµ

0.29

groundColor

0.27

_hid

0.27

iset

0.26

.setHorizontalGroup

0.26

æ°´çĶµ

0.26

_checked

0.25

ä¸įä¿¡

0.25

å±Ĭæ¯ķä¸ļçĶŁ

0.25

Activations Density 0.329%

.

No Comments

No Known Activations