© 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. 54596
    Prev
    Next
    INDEX
    Explanations

    selectivity

    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
     point
    -0.09
    es
    -0.09
    igm
    -0.08
     Point
    -0.08
    esy
    -0.08
    -point
    -0.07
    ry
    -0.07
    point
    -0.07
    ات
    -0.07
    cade
    -0.07
    POSITIVE LOGITS
     friendly
    0.10
    uez
    0.10
     Gra
    0.10
     intern
    0.10
    friendly
    0.09
    Į¨
    0.09
     Friendly
    0.09
    endregion
    0.09
    ayah
    0.09
    Against
    0.09
    Activations Density 0.010%

    No Known Activations