INDEX

Explanations

to

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.setHeader

-0.32

ZE

-0.30

å¤´

-0.28

alto

-0.28

é¡¶

-0.27

à¹Ĥà¸ķ

-0.26

ONTAL

-0.26

(MAX

-0.26

eting

-0.26

BED

-0.25

POSITIVE LOGITS

çĶ¸

0.29

æ´¼

0.29

å½±

0.29

 grounds

0.27

æľĢä½İ

0.27

 Graves

0.27

urv

0.27

èĥį

0.26

åĬŁ

0.26

iggers

0.25

Activations Density 0.105%

to

No Comments

No Known Activations