INDEX

Explanations

out

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

-meta

-0.27

.setter

-0.26

èĸĦå¼±

-0.26

CTYPE

-0.26

ä¸Ĭæľī

-0.25

 dá»«ng

-0.25

è¾¹

-0.25

.assets

-0.25

onnÃ©

-0.25

ettes

-0.24

POSITIVE LOGITS

ä½łä¼ļåıĳçİ°

0.27

checksum

0.27

è®³

0.25

å¸ĺ

0.25

itch

0.25

Chip

0.25

irect

0.24

 chip

0.24

 Maid

0.23

 Diagnosis

0.23

Activations Density 0.003%

out

No Comments

No Known Activations