© 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. 54819
    Prev
    Next
    INDEX
    Explanations

    programming keywords and multilingual text placeholders

    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
    -pr
    -0.07
    eler
    -0.07
    FIELDS
    -0.07
     Pole
    -0.07
    ENO
    -0.07
    unks
    -0.07
    aurus
    -0.06
    idine
    -0.06
     pole
    -0.06
    angel
    -0.06
    POSITIVE LOGITS
     moder
    0.11
    Ìģ
    0.11
     rel
    0.11
    ablo
    0.10
    inand
    0.10
    irty
    0.10
    imator
    0.09
    amer
    0.09
     Dalton
    0.09
     /*!
    0.09
    Activations Density 0.043%

    No Known Activations