neuron-explorer
Steering-first neuron explorer for Qwen3.5-4B: push every MLP neuron, keep every rollout, browse the results
翻譯準備中
一個耐用的工作流程引擎,無重播且無確定性規則:工作流程是資料,而非程式碼。只需一個 JAR 加上資料庫;內建細胞式分片。
AI 翻譯
A durable workflow engine with no replay and no determinism rules: the workflow is data, not code. One JAR plus a database; cellular sharding built in.
開發工具Java · PythonGitHub @hadielmougy上線中營運者未確認
試用過了嗎? 點一下就好,不需要登入。
適用於 JVM 的細胞式耐用工作流程引擎
AI 翻譯
Cellular durable workflow engine for the JVM
取自儲存庫 README
正在載入完整 README。 以下為已儲存的摘錄。
Durable workflows.
Describe a process as a graph. Wiggle runs it as a durable state machine that survives
crashes, waits for humans, and retries failures — with a server you can embed, and workers in
the language you already use.
That's a complete, durable, parallel workflow. No YAML, no DSL files, no determinism rules
to memorize — a compiled graph the server owns, and plain Java methods (or Go, or Python) that
serve its steps.檢視完整 README ↗目前無法載入完整 README。請透過原文連結閱讀。 以下為已儲存的摘錄。
Durable workflows.
Describe a process as a graph. Wiggle runs it as a durable state machine that survives
crashes, waits for humans, and retries failures — with a server you can embed, and workers in
the language you already use.
That's a complete, durable, parallel workflow. No YAML, no DSL files, no determinism rules
to memorize — a compiled graph the server owns, and plain Java methods (or Go, or Python) that
serve its steps.檢視完整 README ↗