© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3899
    Prev
    Next
    INDEX
    Explanations

    predictions and forecasts

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Statue
    -0.11
    ÑģÑĤи
    -0.11
    ágina
    -0.11
    tru
    -0.10
    prov
    -0.10
     vmin
    -0.10
    (Unknown
    -0.10
     proced
    -0.09
     rapp
    -0.09
    izia
    -0.09
    POSITIVE LOGITS
     predictions
    0.23
     prediction
    0.23
     predicting
    0.22
     predicts
    0.22
    Prediction
    0.19
     Prediction
    0.19
     Predict
    0.18
     forecasts
    0.17
     predicted
    0.17
     forecasting
    0.17
    Activations Density 0.356%

    No Known Activations