© 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. 775
    Prev
    Next
    INDEX
    Explanations

    e.g. 'subfamilies', 'families'

    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
     """.
    -0.10
    chestra
    -0.08
    pen
    -0.08
     Bare
    -0.08
     Abbott
    -0.08
     pen
    -0.08
    áºŃt
    -0.07
    Breadcrumb
    -0.07
     Bust
    -0.07
    neau
    -0.07
    POSITIVE LOGITS
    /Area
    0.08
     (--
    0.08
    geb
    0.08
    _sdk
    0.08
    apons
    0.08
     stom
    0.08
    лад
    0.08
    .Formatter
    0.08
    ashi
    0.08
     Gest
    0.08
    Activations Density 0.693%

    No Known Activations