© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 56500
    Prev
    Next
    INDEX
    Explanations

    code constructs and variable names

    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
    nell
    -0.09
     Mean
    -0.09
     con
    -0.09
     wh
    -0.08
    ","",
    -0.08
    rlen
    -0.07
    /single
    -0.07
     Yak
    -0.07
    uren
    -0.07
    .Email
    -0.07
    POSITIVE LOGITS
     includ
    0.10
     Ou
    0.10
     proto
    0.09
    ker
    0.09
     halftime
    0.09
     instal
    0.09
    lectric
    0.09
     {↵↵↵↵
    0.09
    tro
    0.09
    deb
    0.09
    Activations Density 0.007%

    No Known Activations