INDEX

Explanations

bl

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

æ¡Ī

-0.26

 ÑĢÐµÑĪ

-0.26

Has

-0.26

Present

-0.24

CASE

-0.24

#undef

-0.23

 Port

-0.23

.rect

-0.23

 priced

-0.23

ved

-0.23

POSITIVE LOGITS

earer

0.28

.routing

0.27

å·¥ä½ľæľºåĪ¶

0.26

æĪĲéķ¿ä¸º

0.26

 scramble

0.25

-million

0.25

RequiredMixin

0.25

atedRoute

0.25

otics

0.24

çĽ®çļĦåľ¨äºİ

0.24

Activations Density 0.002%

bl

No Comments

No Known Activations