© 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. 4314
    Prev
    Next
    INDEX
    Explanations

    an/a followed by [word]

    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
     Along
    -0.08
     Howe
    -0.07
     carving
    -0.07
     drastic
    -0.07
    ette
    -0.07
    oppel
    -0.07
     toss
    -0.07
    reso
    -0.07
     slight
    -0.07
     pair
    -0.06
    POSITIVE LOGITS
     system
    0.14
     environment
    0.12
     alphabet
    0.12
     economy
    0.11
    system
    0.11
     arsenal
    0.11
    changing
    0.11
    ç³»ç»Ł
    0.11
    -system
    0.10
    allax
    0.10
    Activations Density 0.306%

    No Known Activations