© 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. 4185
    Prev
    Next
    INDEX
    Explanations

    mathematical problem phrasing

    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
    versions
    -0.09
     defence
    -0.08
    olan
    -0.08
    entries
    -0.08
    incident
    -0.08
    GE
    -0.08
    WD
    -0.08
     fro
    -0.08
    wick
    -0.08
    âĢ
    -0.08
    POSITIVE LOGITS
     sui
    0.09
    iesz
    0.09
    csi
    0.09
    oga
    0.08
     ado
    0.08
     finally
    0.08
    dsa
    0.08
    /testing
    0.08
     tip
    0.08
     Morse
    0.08
    Activations Density 0.023%

    No Known Activations