INDEX

Explanations

code/technical documentation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

the

-0.30

 Constitutional

-0.29

 constitutional

-0.29

er

-0.26

omin

-0.26

ëŀĢ

-0.26

ere

-0.25

åħ¼

-0.25

 transit

-0.25

ç»ı

-0.25

POSITIVE LOGITS

.shtml

0.36

reet

0.27

anson

0.27

Opr

0.27

å¾Īæĺİæĺ¾

0.25

REET

0.25

çŃīæĥħåĨµ

0.25

rell

0.24

 ITEMS

0.24

’:

0.24

Activations Density 0.134%

code/technical documentation

No Known Activations