© 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. 1684
    Prev
    Next
    INDEX
    Explanations

    order, size, length, degree

    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
    ÑĤиÑĢа
    -0.08
    æĸ°åĬłåĿ¡
    -0.07
    åĪĨç±»åı·
    -0.07
    ([{
    -0.07
    俱ä¹IJéĥ¨
    -0.07
    éĻĦä¸Ĭä¸Ģ
    -0.07
    æ£ł
    -0.07
    aid
    -0.07
    ondi
    -0.07
    æľ¬é¡µ
    -0.07
    POSITIVE LOGITS
     _______,
    0.09
     apapun
    0.09
     appunto
    0.08
    à¸ķà¹Īาà¸ĩà¹Ĩ
    0.07
    “
    0.07
     tertentu
    0.07
    obra
    0.07
    sthrough
    0.07
    prü
    0.07
    iefs
    0.07
    Activations Density 0.030%

    No Known Activations