INDEX

Explanations

mostly, start, most

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

rist

-0.30

DMETHOD

-0.26

éķĬ

-0.26

ableView

-0.25

Dil

-0.25

æ¨½

-0.25

åľ°çĲĥ

-0.24

unused

-0.24

 tendÃªncia

-0.24

USES

-0.24

POSITIVE LOGITS

_pb

0.27

·¨

0.26

ÑīÐµ

0.26

arrays

0.26

Lane

0.25

ç»Ļå¥¹

0.25

ads

0.25

ITIVE

0.24

æİ´

0.24

.ads

0.23

Activations Density 0.056%

mostly, start, most

No Comments

No Known Activations