← Python API
vraven.decompiler · class

ConceptSet

ConceptSet(node_id: 'str', node_name: 'str', depth: 'float', feature_axis: 'int', concepts: 'list[Concept]', scores: 'np.ndarray', method: 'str', reconstruction_error: 'float', explained_variance: 'float', feature_count: 'int', sample_count: 'int', activation_mean: 'np.ndarray | None' = None, activation_std: 'np.ndarray | None' = None, scoring_weight: 'np.ndarray | None' = None, scoring_bias: 'np.ndarray | None' = None, scoring_nonlinearity: 'str' = 'identity', scoring_topk: 'int | None' = None, metadata: 'dict[str, Any]' = <factory>) -> None

ConceptSet(node_id: 'str', node_name: 'str', depth: 'float', feature_axis: 'int', concepts: 'list[Concept]', scores: 'np.ndarray', method: 'str', reconstruction_error: 'float', explained_variance: 'float', feature_count: 'int', sample_count: 'int', activation_mean: 'np.ndarray | None' = None, activation_std: 'np.ndarray | None' = None, scoring_weight: 'np.ndarray | None' = None, scoring_bias: 'np.ndarray | None' = None, scoring_nonlinearity: 'str' = 'identity', scoring_topk: 'int | None' = None, metadata: 'dict[str, Any]' = <factory>)

Usage

from vraven.decompiler import ConceptSet

value = ConceptSet(...)

Methods

raw_projection_for_score(self, concept_index: 'int', score: 'float') -> 'float'

Translate a fitted concept score into a raw direction coefficient.

score_activation(self, value: 'Tensor') -> 'Tensor'

Project an unseen activation into this set's fitted concept coordinates.

score_component(self, value: 'Tensor', concept_index: 'int') -> 'Tensor'

Public method.

score_for(self, concept_id: 'str') -> 'np.ndarray'

Public method.

Source of truthThis page is generated from the checked-out public symbol, signature, and docstring. Pin the package version for reproducible work.