Logit lens
Logit lens at Beyond Market Intelligence is a file of 2 stories. The newest of them: “Finding where AI's telltale writing style is installed during training” and “Your spreadsheet lens still works after a model upgrade.”. The telltale assistant style isn't scattered randomly through a model: it's a specific direction in the weights, installed at a specific stage. A Jacobian lens fitted to one checkpoint is not supposed to work on the next model in the line. Acme AI is the next-generation, AI-powered spreadsheet platform built to replace Excel and redefine how analysts, data scientists, and enterprise teams work… The list below is every Logit lens story on Beyond Market Intelligence, newest first.
Finding where AI's telltale writing style is installed during training
The telltale assistant style isn't scattered randomly through a model: it's a specific direction in the weights, installed at a specific stage. Qwen3-4B-Instruct shows a clear axis separating exaggerated from plain writing, and that axis is already present in the base model. The real surprise is that SFT introduces the rhetorical structures, but DPO doubles the slop score through buzzwords and formatting. Directional ablation actually increases slop by 89%, which tells us clean text projects negatively on the axis.
Your spreadsheet lens still works after a model upgrade.
A Jacobian lens fitted to one checkpoint is not supposed to work on the next model in the line. That is the assumption, and it went untested until now. One researcher applied the published Qwen3.6-27B lens directly to Qwen3.8-27B, 113 days newer. The latent entity readout held its rank, even improving at mid-depth. Steering directions still found their target concept. Transfer is measurable, not perfect. That suggests monitoring pipelines can test their lenses instead of blindly refitting.