© 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. 1669
    Prev
    Next
    INDEX
    Explanations

    numbers following arithmetic operations

    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
    <|fim_suffix|>
    -0.09
     ApplicationException
    -0.08
     SAME
    -0.08
     DOES
    -0.08
    âĢ¦it
    -0.08
     rulings
    -0.08
     RELATED
    -0.08
     Till
    -0.08
    kin
    -0.08
     Simone
    -0.08
    POSITIVE LOGITS
    =\'
    0.11
    uyo
    0.09
    lio
    0.09
    //----------------------------------------------------------------------------↵
    0.09
    aska
    0.09
    _KP
    0.09
     inval
    0.09
    ,},↵
    0.09
     stdClass
    0.08
    sted
    0.08
    Activations Density 0.536%

    No Known Activations