© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 2812
    Prev
    Next
    INDEX
    Explanations

    #CBC, #ccc, #222, #000, #888

    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
     kost
    -0.10
    bung
    -0.09
    DTD
    -0.09
     Pel
    -0.09
    ceased
    -0.09
    azzi
    -0.09
    /Peak
    -0.08
     gele
    -0.08
    itime
    -0.08
    /we
    -0.08
    POSITIVE LOGITS
    quisitions
    0.09
    -screen
    0.08
    thew
    0.08
    wid
    0.08
     tight
    0.08
     heats
    0.07
     Tight
    0.07
     heat
    0.07
    Outside
    0.07
     welcoming
    0.07
    Activations Density 0.022%

    No Known Activations