© 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. 56585
    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
    寰
    -0.08
     reparti
    -0.08
    ç³»
    -0.07
    ipper
    -0.07
    è¿Ļä¸Ģ天
    -0.07
    lanz
    -0.07
    身æīĭ
    -0.07
     departing
    -0.07
     Bing
    -0.07
    .parents
    -0.07
    POSITIVE LOGITS
    æľ¬èģĮå·¥ä½ľ
    0.07
    _POINT
    0.07
    udit
    0.07
    代çIJĨ
    0.07
    _STREAM
    0.07
    ermann
    0.07
    ë°ķ
    0.06
    Foreground
    0.06
     Streams
    0.06
    å¹³åĩ¡çļĦ
    0.06
    Activations Density 0.000%

    No Known Activations