Research Use Only - Validated Results

SAE Intelligence: Interpretable Genomic Features

Go beyond the score. See the exact biological features—exons, TF motifs, protein structures—that drive a prediction and understand *why* a variant is disruptive.

Why It Matters

  • Transform black-box predictions into transparent, biologically-grounded stories

What We Delivered

  • Clear biological explanations for every prediction

Core Capabilities

From feature attribution to activation steering

Feature Attribution (Live)

LIVE

Technical

We simulate the extraction of active SAE features for a given sequence and calculate the change in log-likelihood (ΔLL) caused by a variant.

Scientific

Connects the model's internal logic to human-readable biological concepts (RUO).

Business

- Trust: Defend and document decisions with feature-linked, quantitative explanations.

Use Cases

Today:
1.Interactive feature tracks in our DynamicOracleExplain component.
2.Quantitative disruption scores to rank a variant's impact.

Prompt Safety (Live)

LIVE

Technical

Detect low‑complexity repeats and other pathological attractors; flag viral/sensitive content (aligned with Forge safety gates).

Scientific

Reduces junk outputs and improves the reliability of generative demos.

Business

- Quality: Fewer dead‑ends in design flows and cleaner, more compelling demos.

Use Cases

Today:
1.Automated safety checks on design inputs, with clear user warnings.

Activation Steering (Roadmap)

ROADMAP

Technical

Expose endpoints to nudge/target feature activations (e.g., chromatin patterns, motif presence) with compute‑aware beam search.

Scientific

Maps CrisPRO.ai‑style inference‑time scaling to controllable design objectives.

Business

- Control: Achieve predictable design quality scaling with transparent, auditable controls.

Use Cases

Roadmap:
1.Steer generation towards desired feature sets; measure quality and efficacy metrics.

Interactive Demonstrations

See SAE Intelligence in action

Feature Overlay Visualization

Toggle Features:

Genomic Sequence (43044290-43044450):

Feature Types:

Exon
Intron
TFBS
Structure
Motif

Disruption Scores (ΔLL)

4
Features
2
High Impact
25.6
Total ΔLL

Exon Boundary

High Impact

-12.5
ΔLL

TF Motif (AP-1)

High Impact

-8.2
ΔLL

Secondary Structure

Medium Impact

-3.1
ΔLL

Splice Site

Low Impact

-1.8
ΔLL

Key Insight:

The ΔLL (Delta Log-Likelihood) score quantifies how much a variant disrupts each biological feature. Negative values indicate disruption, with more negative values showing greater impact.

Prompt Safety Checker

2
Check Types
0
Safe Patterns
1
High Risk

Key Benefits:

  • • Prevents pathological inputs that could generate junk outputs
  • • Flags low-complexity repeats and ambiguous sequences
  • • Improves reliability of generative AI demonstrations
  • • Provides clear suggestions for sequence improvement

Activation Steering (Roadmap)

Roadmap Feature

Overall Progress

46% Complete

AP-1 Binding Sites

Transcription factor binding motifs

TFBS
Current:
0.3

Open Chromatin

Accessible chromatin regions

Chromatin
Current:
0.5

Alpha Helix

Protein secondary structure

Structure
Current:
0.2

Roadmap Feature

Activation steering is currently in development. This demo shows the planned interface for controlling feature activations during generation, with compute-aware beam search and predictable quality scaling.

Planned Benefits:

  • • Steer generation towards desired biological features
  • • Predictable quality scaling with transparent controls
  • • Compute-aware beam search for efficient generation
  • • Auditable design process with clear provenance

Observed Outcomes

Clearer "why" lines on variant reports, linked directly to biological features.
Fewer junk outputs in design flows via the integrated safety checker.
Increased stakeholder trust, as interpretable overlays reduce black‑box concerns.

Ready to See SAE Intelligence in Action?

Experience interpretable AI that explains every prediction