© 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. 45051
    Prev
    Next
    INDEX
    Explanations

    non-English characters and symbols

    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
    ç§ijæĬĢä¼ģä¸ļ
    -0.07
    enson
    -0.07
     %{
    -0.07
    ffb
    -0.06
    æ±Łè·¯
    -0.06
    áĢ±áĢ¬áĢĦáĢº
    -0.06
    ä¸İä¿¡æģ¯
    -0.06
    ison
    -0.06
    ä¸İ伦
    -0.06
     reper
    -0.06
    POSITIVE LOGITS
    idy
    0.08
    عب
    0.07
    zzi
    0.07
    εί
    0.07
    awah
    0.07
    Ùĩرة
    0.07
    é³Į
    0.07
    æľªç»ıåħģ许
    0.07
     pierced
    0.07
    èĥ½å¤ŁåģļåĪ°
    0.07
    Activations Density 0.005%

    No Known Activations