© 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. 47075
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ°§åĮĸ碳
    -0.08
    kog
    -0.07
     suscept
    -0.07
    oppen
    -0.07
    次äºİ
    -0.07
    _except
    -0.07
    mong
    -0.07
    è·¯éĢı
    -0.07
    ikov
    -0.07
    .ms
    -0.07
    POSITIVE LOGITS
    ä¸įæĢĿ
    0.07
    ä¸Ģç»ıåıijçİ°
    0.07
    çĽ²
    0.07
     ni
    0.07
    elai
    0.06
    à¸Ĺิ
    0.06
    edir
    0.06
     Dall
    0.06
    (branch
    0.06
     Shr
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.