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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 than

-0.63

-than

-0.56

_than

-0.49

than

-0.46

 THAN

-0.42

Than

-0.40

 Than

-0.40

 niÅ¼

-0.38

_THAN

-0.33

resher

-0.29

POSITIVE LOGITS

illos

0.27

ä¸Ģèº«

0.27

ä¿ĿæĬ¤åĮº

0.26

illions

0.26

èī¯å¥½çļĦ

0.26

å¾Ĥ

0.26

å¼ºåĬ²

0.25

 negatives

0.24

IBUTES

0.24

bery

0.24

Activations Density 1.480%

more

No Comments

No Known Activations