Hidden but not Opaque: Representation–Behavior Dissociation in Latent Reasoning Models

Latent reasoning models replace human-readable chain-of-thought with computation in continuous hidden states, removing the token-level artifact mechanistic interpretability usually relies on. We ask whether the resulting hidden states remain interpretable, and whether a more capable latent substrate can be trained. Applying tuned lenses, linear probes, pass-level causal interventions, and same-output probes to released CODI checkpoints and in-house CODI-style Qwen3-4B and COCONUT-style Llama 3.1 8B models, we find three representation–behavior dissociations. (i) Decodable ≠ readable: a tuned lens trained on ordinary text decodes structured content from latent states (top-10 detection ≈22%) where the plain logit lens stays near zero. (ii) Causally loaded ≠ behaviorally useful: pass-level ablations show distributed causal load, yet the latent mechanism loses to the explicit-CoT fallback it displaces (57.3% vs. 74.0%). (iii) Output-equivalent ≠ representation-equivalent: on same-output subsets framing stays decodable (AUC up to 0.965), and a probe trained on neutral states transfers to biased states at AUC 0.976 where the model has output a planted wrong answer. Turning from interpreting latent reasoners to building one, we introduce a control battery—compute-matched baselines, ablation, shuffle/matched-random controls, and a bits-per-byte deployment gate—over roughly eighty post-training recipes and fifty-six from-scratch architectures: the mechanism is real and causal but does not beat a compute-matched baseline, a gap our evidence is consistent with closing at larger scale. Hidden-state monitoring is thus a viable interpretability primitive even while the mechanism underneath remains immature.