Therefore I am. I Think

Abstract

We consider the question: when a large language reasoning model makes a choice, did it think first and then decide to, or decide first and then think? In this paper, we present evidence that detectable, early-encoded decisions shape chain-of-thought in reasoning models. Specifically, we show that a simple linear probe successfully decodes tool-calling decisions from pre-generation activations with very high confidence, and in some cases, even before a single reasoning token is produced. Activation steering supports this causally: perturbing the decision direction leads to inflated deliberation, and flips behavior in many examples (between 7 - 79% depending on model and benchmark). We also show through behavioral analysis that, when steering changes the decision, the chain-of-thought process often rationalizes the flip rather than resisting it. Together, these results suggest that reasoning models can encode action choices before they begin to deliberate in text.

Figures (15)

• Figure 1: Overview of our methodology. Linear probes detect action decisions. We apply steering vectors, and measure quantitative as well as behavioral impact on CoT.
• Figure 2: Decision predictability using probes at layer 20 for Qwen3-4B and GLM-Z1-9B. Both models exhibit a dip at around 5% of the reasoning trace.
• Figure 3: Agreement ratio between decisions detected by probe at layer 20 for various stages and think_end tokens, and correctness, for Qwen3-4B and GLM-Z1-9B.
• Figure 4: Example of injection steering (Qwen3-4B) that forces a tool call when the baseline response is to abstain.
• Figure 5: Probe AUROC across sampled layers and generation positions on When2Call for the two main models, Qwen3-4B and GLM-Z1-9B. In both cases, the strongest probes appear in mid-to-late layers, with strong pre_gen predictability and a dip around 5% to 10% of the reasoning trace.