INDEX

Explanations

General "affairs" (topics)

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·¥ä½ľæĬ¥åĳĬ

-0.29

ãĥ²

-0.28

ussian

-0.27

à¸Ķà¸£

-0.25

ounty

-0.24

å¼¹

-0.23

è³ĵ

-0.23

è½¬ç§»

-0.23

adata

-0.23

 currency

-0.23

POSITIVE LOGITS

 Milky

0.27

HITE

0.25

judge

0.25

layers

0.25

ä¸Ńåħ³

0.24

apore

0.24

CCI

0.24

blk

0.24

ationToken

0.24

ESCO

0.24

Activations Density 0.002%

General "affairs" (topics)

No Comments

No Known Activations