© 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. 19072
    Prev
    Next
    INDEX
    Explanations

    normal, Gaussian distribution

    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
    ewear
    -0.08
     viss
    -0.07
    è®©æĽ´å¤ļçļĦ
    -0.07
     sini
    -0.07
    æģĻ
    -0.07
    çĽı
    -0.07
    棱è§Ĵ
    -0.07
    碼
    -0.07
     ÙĥاÙħ
    -0.07
    æĿİè½»
    -0.07
    POSITIVE LOGITS
    anna
    0.07
    aussian
    0.07
    /apple
    0.07
    -like
    0.07
     Gaussian
    0.07
    rzy
    0.06
    -shaped
    0.06
    ä¸įä¿¡
    0.06
    ische
    0.06
    getVar
    0.06
    Activations Density 0.015%

    No Known Activations