© 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. 3942
    Prev
    Next
    INDEX
    Explanations

    CSS class names and HTML tags

    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
     Bun
    -0.08
     confront
    -0.07
    han
    -0.07
     bun
    -0.06
     familiar
    -0.06
     toll
    -0.06
     dém
    -0.06
    æļ
    -0.06
    arring
    -0.06
    msp
    -0.06
    POSITIVE LOGITS
    UDIO
    0.11
    .program
    0.10
     generously
    0.10
    _CUR
    0.10
     rule
    0.10
     aba
    0.10
     Ames
    0.10
     academy
    0.10
    æł
    0.10
     GENERAL
    0.10
    Activations Density 0.119%

    No Known Activations