HF Model & Benchmark Matrix

24,078 variants · 14,984 scores · 120 benchmarks

SAE-Res-Qwen3.5-35B-A3B-Base-W128K-L0_100

Qwen/SAE-Res-Qwen3.5-35B-A3B-Base-W128K-L0_100

kind
original
quant
bf16 (16-bit)
family
qwen
modality
—
root model
Qwen/Qwen3.5-35B-A3B-Base
provider
Qwen
license
other
language
en
context
—
library
—
vRAM (GB)
—
size on disk
—
downloads
86
likes
9
created
—
last modified
2026-05-13T09:43:12+00:00 (2026)
huggingface
https://huggingface.co/Qwen/SAE-Res-Qwen3.5-35B-A3B-Base-W128K-L0_100
tags
topk_saesparse-autoencodersaemechanistic-interpretabilityinterpretabilityqwen-scopearxiv:2605.11887enbase_model:Qwen/Qwen3.5-35B-A3B-Basebase_model:finetune:Qwen/Qwen3.5-35B-A3B-Baselicense:otherregion:us

Benchmark scores (0)

no scores extracted for this variant.

Discussions (0)

none scraped.

Hugging Face model & benchmark data scraped & matrix-ified. 24,078 variants · 14,984 scores · 120 benchmarks.