vulnerable_code_qwen_coder_topk_16384

rufimelo/vulnerable_code_qwen_coder_topk_16384

vulnerable_code_qwen_coder_topk_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 1 Sparse Autoencoder(s) (SAE) trained using SAELens.

Downloads · 30 days

Access

Public

Updated Mar 12, 2026

Repo size

822 MB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors822 MB · 100%

At a glance

Library: sae_lens
Access: Public
Created: Mar 12, 2026
Updated: Mar 12, 2026
SHA: d5611305

Model card

From the Hugging Face model README

Sparse Autoencoders for Qwen/Qwen2.5-7B-Instruct

This repository contains 1 Sparse Autoencoder(s) (SAE) trained using SAELens.

Model Details

Property	Value
Base Model	`Qwen/Qwen2.5-7B-Instruct`
Architecture	`topk`
Input Dimension	3584
SAE Dimension	28672
Training Dataset	`TQRG/DeltaSecommits_qwen-2.5-7b-instruct_tokenized_v2_vulnerable`

Available Hook Points

Hook Point
`blocks.11.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/vulnerable_code_qwen_coder_topk_16384",
    sae_id="blocks.11.hook_resid_post"  # Choose from available hook points above
)

# Use with TransformerLens
from transformer_lens import HookedTransformer

model = HookedTransformer.from_pretrained("Qwen/Qwen2.5-7B-Instruct")

# Get activations and encode
_, cache = model.run_with_cache("your text here")
activations = cache["blocks.11.hook_resid_post"]
features = sae.encode(activations)

Files

blocks.11.hook_resid_post/cfg.json - SAE configuration
blocks.11.hook_resid_post/sae_weights.safetensors - Model weights
blocks.11.hook_resid_post/sparsity.safetensors - Feature sparsity statistics

Training

These SAEs were trained with SAELens version 6.26.2.

Library: sae_lens
Created: Mar 12, 2026
Updated: Mar 12, 2026