narrow steer band, assert >=20 train, training table, full gen dumps

Root cause found via diag_axis on 4B: raw mean-diff steered across the 7-layer
band (0.4-0.6) at coeff=1 DESTROYS gemma-3-4b (coherence 1.00->0.02). That
starved the filter to 2 kept completions, so the "adapter" was ~untrained
(2 examples) = base behaviour, my Q1 "promising" read was not validated.

Fixes:
- separate steer_layers (narrow 0.45-0.55) for the vector from layer_range
  (broad 0.0-1.0) for the LoRA; they were wrongly coupled
- lower alpha sweep (0.25,0.5,1,2); n_prompts=16
- assert len(kept) >= min_train(20); TINY=2. Don't train on starved data.
- heal training table (loguru+tqdm per token-efficient-logging): step, nll, kl,
  loss, gnorm + SHOULD
- full untruncated steer + adapter generation dumps with prompt and
  coherence(p_ans_any) inline so we can judge coherence/trait ourselves

NOT yet run with fixes on 4B. Base 4B is Care=0.92 (already aligned) -> the
prompting-baseline confound (Q7) is now the critical check.

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

scripts/diag_axis.py

@@ -16,8 +16,8 @@ sys.path.insert(0, "src")
 from steer_heal.config import RunConfig  # noqa: E402
 from steer_heal.steering import teacher_vec  # noqa: E402
 
-MODEL = "google/gemma-3-1b-it"
-cfg = RunConfig(model=MODEL, n_prompts=12)
+cfg = RunConfig(n_prompts=12)  # default model (gemma-3-4b-it)
+MODEL = cfg.model
 
 tok = AutoTokenizer.from_pretrained(MODEL)
 if tok.pad_token is None: