find_topics returns the same topics for any keywords

Nobody has claimed this yet.

Hello,
I have fit the BERTopic model using CUML's HDBSCAN and UMAP. I used `microsoft/codebert-base` on huggingface as the embedding model like this:

```python
model = pipeline("feature-extraction",
model="microsoft/codebert-base",
device=0)
topic_model = BERTopic(embedding_model=model,
umap_model=umap_model,
hdbscan_model=hdbscan_model,
calculate_probabilities=True,
)
topic_model = topic_model.fit(docs)

topic_model.save("models/codebert",
serialization="safetensors",
save_ctfidf=True)
```

The above code runs without any problems. This is how I load the model:

```python
embedding_model = 'microsoft/codebert-base'
model = pipeline('feature-extraction', embedding_model)
model = HFTransformerBackend(model)
topic_model = BERTopic.load("models/codebert",
embedding_model=model)
```

Although invoking the get_topic_info method from topic_model returns a list of meaningful topics, when I call find_topics, no matter what the term is, a list of the same topics is returned with almost the same probabilities. The same thing happened when I used another Huggingface model. Are there any potential workarounds?

Start with BERTopic.find_topics and the BERTopic.load/HFTransformerBackend path, using the CodeBERT and CUML HDBSCAN/UMAP setup shown in the report. Compare find_topics results for different keywords with get_topic_info output and verify whether loading preserves the embedding behavior; done means keyword searches return meaningfully different topics or the limitation is documented.

Written by the indexing model from the issue text.