Downloads · 30 days
0
secure_code_qwen_coder_topk_cl_16384
rufimelo/secure_code_qwen_coder_topk_cl_16384
secure_code_qwen_coder_topk_cl_16384 is a machine learning model from rufimelo. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for sae_lens.
This repository contains 3 Sparse Autoencoder(s) (SAE) trained using SAELens.
Access
Public
Updated Feb 16, 2026
Repo size
1.4 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors1.9 GB · 100%
At a glance
- Library
- sae_lens
- Access
- Public
- Created
- Feb 16, 2026
- Updated
- Feb 16, 2026
- SHA
- 584fe754
Model card
From the Hugging Face model README
Sparse Autoencoders for Unknown
This repository contains 3 Sparse Autoencoder(s) (SAE) trained using SAELens.
Model Details
| Property | Value |
|---|---|
| Base Model | Unknown |
| Architecture | topk |
| Input Dimension | 3584 |
| SAE Dimension | 16384 |
| Training Dataset | Unknown |
Available Hook Points
| Hook Point |
|---|
blocks.0.hook_resid_post |
blocks.14.hook_resid_post |
blocks.27.hook_resid_post |
Usage
from sae_lens import SAE
# Load an SAE for a specific hook point
sae, cfg_dict, sparsity = SAE.from_pretrained(
release="rufimelo/secure_code_qwen_coder_topk_cl_16384",
sae_id="blocks.0.hook_resid_post" # Choose from available hook points above
)
# Use with TransformerLens
from transformer_lens import HookedTransformer
model = HookedTransformer.from_pretrained("Unknown")
# Get activations and encode
_, cache = model.run_with_cache("your text here")
activations = cache["blocks.0.hook_resid_post"]
features = sae.encode(activations)
Files
blocks.0.hook_resid_post/cfg.json- SAE configurationblocks.0.hook_resid_post/sae_weights.safetensors- Model weightsblocks.0.hook_resid_post/sparsity.safetensors- Feature sparsity statisticsblocks.14.hook_resid_post/cfg.json- SAE configurationblocks.14.hook_resid_post/sae_weights.safetensors- Model weightsblocks.14.hook_resid_post/sparsity.safetensors- Feature sparsity statisticsblocks.27.hook_resid_post/cfg.json- SAE configurationblocks.27.hook_resid_post/sae_weights.safetensors- Model weightsblocks.27.hook_resid_post/sparsity.safetensors- Feature sparsity statistics
Training
These SAEs were trained with SAELens version 6.26.2.
- Library
- sae_lens
- Created
- Feb 16, 2026
- Updated
- Feb 16, 2026