© 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. 56717
    Prev
    Next
    INDEX
    Explanations

    object creation and descriptions

    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
    anca
    -0.10
     Corm
    -0.09
     sta
    -0.09
    .har
    -0.09
     INS
    -0.09
    esti
    -0.09
    .'''↵
    -0.09
     marks
    -0.09
    .TestCase
    -0.09
     stati
    -0.09
    POSITIVE LOGITS
     consum
    0.10
    )._
    0.09
     dich
    0.08
     bian
    0.08
    itta
    0.07
    tele
    0.07
    êt
    0.07
     Federal
    0.07
    sie
    0.07
     Ru
    0.07
    Activations Density 0.010%

    No Known Activations