INDEX

Explanations

place names

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

acies

-0.29

åİ¢

-0.28

 contag

-0.27

veal

-0.27

iverse

-0.26

omed

-0.26

 vast

-0.25

kest

-0.25

ç¼ł

-0.25

åİĤ

-0.25

POSITIVE LOGITS

 Cursors

0.27

Disposition

0.26

ordan

0.26

uner

0.25

çīĿ

0.25

LOY

0.25

dsn

0.25

 parch

0.24

Wa

0.24

itemid

0.24

Activations Density 0.004%

place names

No Comments

No Known Activations