INDEX

Explanations

uptake

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¸«

-0.28

 flown

-0.27

å¸Ī

-0.26

åłĤ

-0.26

abyrinth

-0.25

eu

-0.25

asca

-0.25

æ¨¡ç³Ĭ

-0.25

.types

-0.25

ä½¿ãģĦ

-0.24

POSITIVE LOGITS

çļĤ

0.24

 Ð·Ð°Ð½

0.24

finalize

0.24

éĶĹ

0.24

#line

0.23

 Hamilton

0.23

Corner

0.23

ighet

0.23

é¡·

0.23

unting

0.23

Activations Density 0.008%

uptake

No Comments

No Known Activations