INDEX

Explanations

new

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_31.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.31.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æ»´

-0.34

ale

-0.29

staff

-0.26

æ£ļ

-0.26

undry

-0.26

æĿĸ

-0.26

Successfully

-0.25

ÑĢÐµÐ±

-0.25

åĽŀå®¶

-0.25

åĽŀåĪ°å®¶

-0.25

POSITIVE LOGITS

 starting

0.33

èµ·

0.32

 start

0.30

$start

0.29

 instances

0.29

è·¯æ¡¥

0.28

_start

0.27

monic

0.27

:start

0.27

OperationContract

0.26

Activations Density 0.052%

new

No Comments

No Known Activations