© 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. 15504
    Prev
    Next
    INDEX
    Explanations

    reversing, replica, mirror, transpose

    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
    åĪĨæĪIJ
    -0.07
    缴æİ¥æĪĸ
    -0.07
    ukt
    -0.07
     multiples
    -0.06
    Multiple
    -0.06
    quier
    -0.06
    cac
    -0.06
     Nass
    -0.06
    yun
    -0.06
    _multiple
    -0.06
    POSITIVE LOGITS
    ernaut
    0.08
    ä¸įæĹ©
    0.08
    _BP
    0.07
     hảo
    0.07
    ายà¸Ļ
    0.07
    utÄĥ
    0.07
    æ£ł
    0.07
    对称
    0.07
     symmetry
    0.07
     tekint
    0.07
    Activations Density 0.012%

    No Known Activations