© 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. 9666
    Prev
    Next
    INDEX
    Explanations

    US Pat, survey conducted, Verizon, article on, research verified

    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
    çİ°å°Ĩæľīåħ³äºĭ项
    -0.08
     obviously
    -0.07
    çİ°åľ¨æĺ¯
    -0.07
    åı¯èĥ½åŃĺåľ¨
    -0.07
    åľ¨å½ĵåīį
    -0.07
     دÙĨباÙĦ
    -0.07
    好象
    -0.07
     jeżeli
    -0.07
    çİ°åľ¨å·²ç»ı
    -0.06
    她çİ°åľ¨
    -0.06
    POSITIVE LOGITS
    åĮ¿åIJį
    0.08
    èĻ½çĦ¶æ²¡æľī
    0.08
    éķ¿è¾¾
    0.08
    尤为
    0.08
    ungg
    0.08
    [((
    0.08
    èĻ½çĦ¶ä¸įæĺ¯
    0.08
    éĿ¢ç§¯è¾¾
    0.07
    å°±æĽ¾
    0.07
    ç½²
    0.07
    Activations Density 0.022%

    No Known Activations