© 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. 54184
    Prev
    Next
    INDEX
    Explanations

    logging.getLogger

    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
    ulan
    -0.12
    fone
    -0.11
    mie
    -0.11
    ymax
    -0.10
     casualty
    -0.10
    uras
    -0.10
    Occurred
    -0.10
    antha
    -0.09
    URE
    -0.09
    asio
    -0.09
    POSITIVE LOGITS
    .getLogger
    0.13
    ueil
    0.08
    ãģĿãģĹãģ¦
    0.08
     Dabei
    0.08
    /by
    0.07
     programmer
    0.07
    oding
    0.07
     Programmer
    0.07
    otts
    0.07
    ss
    0.07
    Activations Density 0.001%

    No Known Activations