© 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. 55258
    Prev
    Next
    INDEX
    Explanations

    C++ class/struct member definition

    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
    ê³
    -0.09
     Briggs
    -0.08
     iter
    -0.08
     particul
    -0.08
    lessly
    -0.08
    antan
    -0.08
    CCCCCC
    -0.08
    beg
    -0.08
    hra
    -0.08
    ×ķ×
    -0.08
    POSITIVE LOGITS
     Folk
    0.09
    ovi
    0.08
    ever
    0.08
     (↵
    0.08
    (↵
    0.08
    _reason
    0.08
     Thesis
    0.08
    mai
    0.07
     Alison
    0.07
    angs
    0.07
    Activations Density 0.043%

    No Known Activations