© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 8750
    Prev
    Next
    INDEX
    Explanations

    code file paths with extensions

    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
    Negative Logits
    ,)↵
    -0.10
     ”↵↵
    -0.08
     Alone
    -0.08
     Asheville
    -0.08
     Sing
    -0.08
     Sculpt
    -0.08
    ych
    -0.08
    input
    -0.08
    -{
    -0.08
    enum
    -0.08
    POSITIVE LOGITS
    ibur
    0.09
    visor
    0.07
     toc
    0.07
     Roc
    0.07
    cial
    0.07
    -tags
    0.07
     Playboy
    0.07
    cion
    0.07
    :{}
    0.07
    ssi
    0.07
    Activations Density 5.445%

    No Known Activations