© 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. 56651
    Prev
    Next
    INDEX
    Explanations

    motion and/or petition

    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
    acades
    -0.10
    uze
    -0.10
     inconvenience
    -0.10
     UTC
    -0.09
     Dj
    -0.09
    trl
    -0.09
    rir
    -0.09
    iry
    -0.09
    ugi
    -0.09
    rze
    -0.09
    POSITIVE LOGITS
     simultaneously
    0.09
     simultaneous
    0.08
    vens
    0.08
     Frost
    0.08
    "↵↵↵↵
    0.07
     satur
    0.07
     Lomb
    0.07
    itas
    0.07
     implicitly
    0.07
     afterwards
    0.07
    Activations Density 0.007%

    No Known Activations