© 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. 57392
    Prev
    Next
    INDEX
    Explanations

    BO, IL, CT, Cañas, DCT, R1, IUD

    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
    .dtd
    -0.07
    ï¼Īç¬ij
    -0.07
     Crack
    -0.07
    cta
    -0.07
    ||(
    -0.07
    vert
    -0.07
     Morg
    -0.07
    ва
    -0.07
    ",-
    -0.07
    /build
    -0.07
    POSITIVE LOGITS
    天
    0.10
    boo
    0.09
     mentioned
    0.09
    ÂĢÂ
    0.09
     Ole
    0.09
    mentioned
    0.09
     (;
    0.09
    bia
    0.08
    tl
    0.08
     aforementioned
    0.08
    Activations Density 0.030%

    No Known Activations