© 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. 4609
    Prev
    Next
    INDEX
    Explanations

    names of presidents and leaders

    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
     minors
    -0.07
     Heck
    -0.07
     Amateur
    -0.06
    Temporary
    -0.06
    ä½ľèĢħ
    -0.06
     Author
    -0.06
     ðŁij
    -0.06
    vd
    -0.06
    ema
    -0.06
     surgeon
    -0.06
    POSITIVE LOGITS
    ?,↵
    0.11
    uju
    0.11
    krit
    0.11
    idar
    0.10
    ’T
    0.10
    [String
    0.10
    ague
    0.10
    ossal
    0.09
    ere
    0.09
    ani
    0.09
    Activations Density 0.462%

    No Known Activations