INDEX

Explanations

locations

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

Mor

-0.28

['__

-0.27

ä¸ĸçķĮè§Ĥ

-0.27

æ¸¸èīĩ

-0.26

pob

-0.26

ubit

-0.26

osci

-0.25

 Morse

-0.25

 carefully

-0.25

 pitched

-0.24

POSITIVE LOGITS

plate

0.30

archs

0.29

plates

0.29

ç¡®

0.27

ming

0.27

 plate

0.26

.realm

0.26

unning

0.26

union

0.25

 plates

0.25

Activations Density 0.020%

locations

No Comments

No Known Activations