INDEX

Explanations

punctuation

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

 currentItem

-0.26

 unrelated

-0.25

ä¸¥éĩįå½±åĵį

-0.25

èĦį

-0.24

 Ø§ÙĦÙģÙĦ

-0.23

ãĥ³ãĤ°

-0.23

Iss

-0.23

 google

-0.23

ç»ĵæŀĦè°ĥæķ´

-0.23

éĢĢ

-0.23

POSITIVE LOGITS

auer

0.30

Ã©l

0.28

cran

0.27

åĬ¡

0.26

ims

0.25

áº¯ng

0.25

spec

0.25

åİ¿å§Ķä¹¦è®°

0.25

cy

0.24

 cleans

0.24

Activations Density 0.766%

punctuation

No Comments

No Known Activations