© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 53871
    Prev
    Next
    INDEX
    Explanations

    predicting scores and risk factors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     tracing
    -0.10
     against
    -0.10
     opin
    -0.09
    against
    -0.09
     nons
    -0.09
     Sor
    -0.09
     Vall
    -0.09
     corr
    -0.09
    verity
    -0.09
    ver
    -0.09
    POSITIVE LOGITS
     predicting
    0.12
     Predict
    0.11
     Prediction
    0.11
     predictor
    0.11
     Conditional
    0.11
     predictors
    0.10
     predicts
    0.10
     predict
    0.10
     predictive
    0.10
     Predictor
    0.10
    Activations Density 0.105%

    No Known Activations