© 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. 8439
    Prev
    Next
    INDEX
    Explanations

    home to

    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
    olan
    -0.08
     gall
    -0.08
    mad
    -0.08
    ot
    -0.08
    ail
    -0.07
     mad
    -0.07
    20
    -0.07
     Bris
    -0.07
    len
    -0.07
     spo
    -0.07
    POSITIVE LOGITS
    /assert
    0.10
    haft
    0.10
    onestly
    0.10
    gos
    0.10
     amore
    0.09
     cabo
    0.09
    loser
    0.09
    .dsl
    0.09
     Few
    0.09
    udi
    0.09
    Activations Density 0.503%

    No Known Activations