Reasoning models often continue generating after producing an answer, yet stopping prematurely may interrupt useful verification or revision. In this work, we investigate whether targeted interventions in a model's internal computation can provide a reliable signal for when to stop reasoning. We introduce Prune-to-Probe, an inference-time controller that uses causal activation interventions to probe the stability of a model's current answer. Specifically, we identify late-MLP coordinates that contribute to post-answer continuation while excluding those important for answer completion. Once an answer is stated, Prune-to-Probe temporarily suppresses the selected coordinates and measures the resulting stopping response relative to matched random interventions. Crucially, these interventions serve only as probes: the model either returns its existing answer or resumes generation from an untouched cache. On MATH, Prune-to-Probe reduces reasoning-token forwards by 2.60%, preserving all naturally correct trajectories while repairing six errors. On MMLU-Pro, it achieves 1.145% pooled savings with no observed harm. Further analysis shows that the intervention captures decision stability rather than correctness (AUROC 0.502). These results demonstrate the potential of causal activation probes for efficient inference-time control without permanent model modification.
Figures & tables
Evaluation
Probe exits (correct / wrong)
Harm / repair
Charged savings
8B MATH held-out
86 (86 / 0)
0 / 6
99.55 (2.60%)
1.7B MMLU-Pro validation
99 (64 / 35)
0 / 4
35.58 (1.267%)
1.7B MMLU-Pro confirmation
91 (55 / 36)
0 / 1
31.12 (1.032%)
Table 1: Main results. Savings are fully charged reasoning-token forwards per trajectory; percentages use natural reasoning forwards as the denominator. A harm changes a naturally correct trajectory to a wrong policy output; a repair changes a naturally wrong trajectory to a correct policy output.
Figure 2: The experimental progression. Panels (a–b) show selected-minus-random local effects in their original units. Panel (c) shows that persistent edits do not produce reliable savings. Panel (d) reports fully charged savings from the bounded probe. Points are means and bars are 95% bootstrap intervals; positive savings indicate lower inference cost.
Appendix figures & tables4 assets
Supplementary material from the paper’s appendix.
Appendix
Qwen3-8B held-out
Qwen3-1.7B initial test
Evaluation trajectories
512
128
Correct pruning accepts
86/86
60/63
Harms / repairs
0 / 6
1 / 6
Charged saving
2.60%
18.04%
Specificity
4.6722
7.4081
Strict protocol
pass
fail
Appendix
Table 2: Results at two model scales. The percentages are not a head-to-head comparison: the models have different natural lengths, neuron doses, and evaluation status.
Metric
Validation
Confirmation
Descriptive union
Trajectories
1,024
1,024
2,048
Natural correct
538
481
1,019
Accepted: correct / wrong
64 / 35
55 / 36
119 / 71
Natural-correct harms / repairs
0 / 4
0 / 1
0 / 5
Charged saving per trajectory
35.58
31.12
33.35
Relative charged saving
1.267%
1.032%
1.145%
Appendix
Table 3: Prospective non-math validation and conditional confirmation. The union is a descriptive analysis conducted after confirmation, not a third confirmatory test. Probe and forced-readout forwards are fully charged.
State
Seed 54 stop effect
Seed 55 stop effect
Candidate-margin effect, seed 54 / 55
Repetition
10.269
7.826
−1.563 / −2.260
Verification
8.864
7.376
−2.233 / −2.264
Revision
7.185
8.657
−0.694 / −0.934
Alternative
8.501
6.566
−1.840 / −2.236
Appendix
Table 4: Target minus the mean of three matched-random interventions in the functional-state pilot. Each cell contains 12 prompts. Full bootstrap intervals are reported in the supplementary statistics.
Experiment
Model / precision
Accelerator
Purpose
8B MATH evaluation
Qwen3-8B / BF16
one A100 80GB PCIe
Validation and held-out evaluation
8B diagnostics
Qwen3-8B / BF16
one L40S
Seed, latency, and endpoint analyses
1.7B localization
Qwen3-1.7B / BF16
one L40S
Model-specific causal localization
1.7B MATH evaluation
Qwen3-1.7B / BF16
one L4
Controller development and confirmation
1.7B non-math evaluation
Qwen3-1.7B / BF16
one L4
Development, validation, and confirmation
Appendix
Table 5: Recorded compute environments. All runs report Python 3.11.12, PyTorch 2.8.0+cu128, and CUDA 12.8. Exact elapsed time was not retained for every historical run, so total project GPU-hours are not estimated.
We provide evidence of performative chain-of-thought (CoT) in reasoning models, where a model becomes strongly confident in its final answer, but continues generating tokens without revealing its internal belief. Our analysis compares activation probing, early forced answering, and a CoT monitor across two large models (DeepSeek-R1 671B & GPT-OSS 120B) and find task difficulty-specific differences: The model's final answer is decodable from activations far earlier in CoT than a monitor is able to say, especially for easy recall-based MMLU questions. We contrast this with genuine reasoning in difficult multihop GPQA-Diamond questions. Despite this, inflection points (e.g., backtracking, 'aha' moments) occur almost exclusively in responses where probes show large belief shifts, suggesting these behaviors track genuine uncertainty rather than learned "reasoning theater." Finally, probe-guided early exit reduces tokens by up to 80% on MMLU and 30% on GPQA-Diamond with similar accuracy, positioning attention probing as an efficient tool for detecting performative reasoning and enabling adaptive computation.
Weight pruning can degrade the accuracy of large reasoning models (LRMs), yet it remains unclear whether it damages reasoning itself. We find that much of this degradation stems from a failure to stop rather than to reason. As sparsity increases, pruned LRMs increasingly fail to terminate within the token budget, often after the correct answer has appeared in their reasoning, instead falling into repetitive loops, even though they still recognize where the dense model would stop. We further find that the hidden-state difference between terminating and looping continuations is consistent across pruned checkpoints, suggesting a shared direction associated with committing to an answer. Building on this, we propose Termination-Guided Activation Steering (TGAS), a training-free method that adds this direction to the residual stream at inference time. Across six LRMs, three pruning pipelines, and math and code benchmarks, TGAS improves termination and overall accuracy while reducing repetitive reasoning and generation length, showing that this failure is actionable.
Reasoning models do not stop when they know the answer. On DeepSeek-R1-Distill-Qwen-7B the chain of thought runs about twice as long as the model's own answer probability takes to settle, and how much of that excess is removable varies from problem to problem, so a global length penalty cannot take it out. We take it out by internalizing a causal interpretability finding into the weights. The mechanism is a halt vector: a difference-of-means direction at layer 18 of this model whose steering strength controls how long it thinks, while a replicated value axis does nothing. Installing that intervention in the weights is harder than it looks. Maximizing the scalar projection onto the direction corrupts the off-axis dimensions a frozen downstream reader depends on, and generation gets longer instead of shorter; what works is reconstructing the whole steered activation with those dimensions pinned to their natural values. Fit from 24 problems and no reinforcement learning, the halt removes about a quarter of the thinking at held accuracy across five unseen benchmarks, and the cut tracks each problem's own removable slack at 0.70. It also closes a non-termination pathology that grows with difficulty and that a decoding-time confidence hook makes worse. We do not claim to beat a well-tuned length penalty or decoding-time early exit on the raw trade-off; the contribution is how the halt is obtained.