© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50624
    Prev
    Next
    INDEX
    Explanations

    Gamma Knife radiosurgery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
    Protect
    -0.07
    Tro
    -0.06
    æĬ
    -0.06
    涨
    -0.06
    çļĦåıĮéĩį
    -0.06
    ÄĽ
    -0.06
    ataka
    -0.06
     Muhammad
    -0.06
     ÑĦла
    -0.06
    éĢĤ度çļĦ
    -0.06
    POSITIVE LOGITS
    ergi
    0.08
    felt
    0.08
    à¹Ģรียà¸ĩ
    0.08
    ีà¸ļ
    0.08
    imba
    0.07
    оÑĤа
    0.07
    éch
    0.07
     privately
    0.07
    /loader
    0.07
    ISCO
    0.07
    Activations Density 0.026%

    No Known Activations