© 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. 45522
    Prev
    Next
    INDEX
    Explanations

    ultrasound

    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
    ieke
    -0.09
    æĹĹé¼ĵ
    -0.08
    ebra
    -0.08
    æ¯Ķåݻ年åIJĮæľŁ
    -0.08
    ever
    -0.08
    ylland
    -0.08
    неÑģÑĤи
    -0.08
    OURNAL
    -0.08
    ελ
    -0.08
    yal
    -0.08
    POSITIVE LOGITS
     hẳn
    0.08
    à¹Ĩ
    0.08
    ÙĨ
    0.07
    thers
    0.07
    íĥĦ
    0.07
    äºĨ对
    0.07
    ÙĬÙĨ
    0.07
    imal
    0.07
    áĥ¡
    0.06
    APTER
    0.06
    Activations Density 0.002%

    No Known Activations