© 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. 4165
    Prev
    Next
    INDEX
    Explanations

    divisibility and factors

    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
    ols
    -0.09
    áŀ¶áŀ
    -0.09
     concent
    -0.09
     nouvel
    -0.09
    /header
    -0.08
    <header
    -0.08
     upd
    -0.08
     dr
    -0.08
    ouce
    -0.08
    Keyboard
    -0.08
    POSITIVE LOGITS
     Âł Âł Âł Âł
    0.09
     finale
    0.08
    pire
    0.08
     meanwhile
    0.08
     segu
    0.08
     >>↵↵
    0.08
     Shib
    0.08
     Âł Âł
    0.08
    sic
    0.08
     recurs
    0.08
    Activations Density 0.054%

    No Known Activations