BluelightAI

bluelightai's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Articles

deqing 

authored a paper 20 days ago

Are LLM Decisions Faithful to Verbal Confidence?

Paper • 2601.07767 • Published 21 days ago • 4

deqing 

submitted a paper to Daily Papers 20 days ago

Are LLM Decisions Faithful to Verbal Confidence?

Paper • 2601.07767 • Published 21 days ago • 4

jakobhansen-blai 

published 2 models 2 months ago

bluelightai/clt-qwen3-1.7b-base-20k

Feature Extraction • Updated Dec 1, 2025

bluelightai/clt-qwen3-0.6b-base-20k

Feature Extraction • Updated Dec 1, 2025 • 14

jakobhansen-blai 

updated a Space 2 months ago

Running

README

🏢

jakobhansen-blai 

published a Space 2 months ago

Running

README

🏢

jakobhansen-blai 

in bluelightai/clt-qwen3-1.7b-base-20k 2 months ago

Create README.md

#1 opened 2 months ago by

jakobhansen-blai

jakobhansen-blai 

in bluelightai/clt-qwen3-0.6b-base-20k 2 months ago

Draft README.md

#1 opened 2 months ago by

jakobhansen-blai

jakobhansen-blai 

updated a collection 2 months ago

Qwen3 Cross-layer Transcoders

Collection

Cross-layer transcoders for models from the Qwen3 family. • 2 items • Updated Dec 1, 2025 • 1

jakobhansen-blai 

updated 2 models 2 months ago

bluelightai/clt-qwen3-1.7b-base-20k

Feature Extraction • Updated Dec 1, 2025

bluelightai/clt-qwen3-0.6b-base-20k

Feature Extraction • Updated Dec 1, 2025 • 14

deqing 

authored a paper 3 months ago

When Do Transformers Learn Heuristics for Graph Connectivity?

Paper • 2510.19753 • Published Oct 22, 2025 • 4

deqing 

authored a paper 6 months ago

Zebra-CoT: A Dataset for Interleaved Vision Language Reasoning

Paper • 2507.16746 • Published Jul 22, 2025 • 35

upup-ashton-wang 

authored a paper 8 months ago

Resa: Transparent Reasoning Models via SAEs

Paper • 2506.09967 • Published Jun 11, 2025 • 21

deqing 

authored 2 papers 8 months ago

Resa: Transparent Reasoning Models via SAEs

Paper • 2506.09967 • Published Jun 11, 2025 • 21

Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models

Paper • 2505.14071 • Published May 20, 2025 • 1

upup-ashton-wang 

authored a paper 9 months ago

Tina: Tiny Reasoning Models via LoRA

Paper • 2504.15777 • Published Apr 22, 2025 • 56

upup-ashton-wang 

authored a paper 10 months ago

AI-University: An LLM-based platform for instructional alignment to scientific classrooms

Paper • 2504.08846 • Published Apr 11, 2025 • 9

deqing 

authored a paper 12 months ago

FoNE: Precise Single-Token Number Embeddings via Fourier Features

Paper • 2502.09741 • Published Feb 13, 2025 • 15