qwen3-30b-a3b-moe-sae
qwen3-30b-a3b-moe-sae is Machine learning model. Download, explore files and run it on Hugging Face.. It is ranked #517 on the AI Radar, in Open & local models, first seen 1 days ago and shared in 1 post (6.4k views).
ByteDance-Seed/Qwen3-30B-A3B-MoE-SAE · Hugging Face Hugging Face Log In Sign Up ByteDance-Seed / Qwen3-30B-A3B-MoE-SAE Like 0 Follow ByteDance Seed 3.69k English sparse-autoencoder sae interpretability mixture-of-experts qwen3 License: apache-2.0 Model card Files Files and versions xet Community Copy to bucket Qwen3-30B-A3B MoE-Output Sparse Autoencoders TopK sparse autoencoders (k = 100, 2^20 latents) trained on the MoE block output of Qwen3-30B-A3B at layers 4, 30 and 46, released with the paper Sparse AutoEncoders Reveal That MoE Experts Exhibit Human-Interpretable Fine-Grained Specialization ( project page , code , paper: TODO). Files…
What people said about qwen3-30b-a3b-moe-sae on X
ByteDance just released sparse autoencoders for Qwen3-30B on Hugging Face These SAEs reveal that mixture-of-experts have fine-grained, interpretable specializations. https://huggingface.co/ByteDance-Seed/Qwen3-30B-A3B-MoE-SAE
— @HuggingPapers, 1 days ago · 56 likes · see the post
Alternatives to qwen3-30b-a3b-moe-sae
- kimi-k3.1-pro — Releasing the model weights of Kimi K3.1 Pro
- niklaslenz.com — Play the world in your browser. Every number, the exact command and the raw output
- unsloth.ai — Guide to running Mistral Large 4 GGUFs locally with Unsloth and llama.cpp.
- project-maya — Plus a round of fixes, UI improvements and community PRs.
- twil-8b — Text Generation model with 9B parameters. Download, explore files and run it on Hugging Face.
- qwen3.8-flash-next-gguf — Image-Text-to-Text model with 177B parameters. Download, explore files and run it on Hugging Face.
qwen3-30b-a3b-moe-sae in numbers
- Rank on the AI Radar: #517 of 10402
- Shared in 1 post by 1 account: @HuggingPapers
- 6.4k views on those posts
- First seen 1 days ago, last shared 1 days ago
- Pricing seen by AGK Intelligence: open source
- Market: Open & local models
FAQ
What is qwen3-30b-a3b-moe-sae?
Machine learning model. Download, explore files and run it on Hugging Face. It was first shared on X 1 days ago and is ranked #517 on the AI Radar.
Is qwen3-30b-a3b-moe-sae free?
It is open source.
Who shared qwen3-30b-a3b-moe-sae?
1 account on X, including @HuggingPapers, in 1 post totalling 6.4k views.
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.6k posts from 5k X accounts over the last 14 days, 10.4k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-06 15:10 UTC. Full method.