© 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. 1447
    Prev
    Next
    INDEX
    Explanations

    distributed software

    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
    
    -0.07
     advers
    -0.07
     Intern
    -0.07
     Bers
    -0.07
     âĢİ
    -0.07
    oi
    -0.06
     pip
    -0.06
     aliqua
    -0.06
    &
    -0.06
    <![
    -0.06
    POSITIVE LOGITS
     hereby
    0.10
    >_
    0.10
     Gas
    0.10
    ./(
    0.10
     (...)
    0.10
    zig
    0.10
    ["+
    0.10
    Gas
    0.10
     justices
    0.09
     debugging
    0.09
    Activations Density 3.195%

    No Known Activations