© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2495
    Prev
    Next
    INDEX
    Explanations

    frequency and response

    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
    åĨ°åĿĹ
    -0.08
    ä¸įåĸĦ
    -0.07
    åIJĮè´¨
    -0.07
    åŃľ
    -0.07
    æ¨Ł
    -0.07
    æ°ijæĦı
    -0.07
    ocy
    -0.07
     Ehr
    -0.07
    ABI
    -0.07
     taboo
    -0.07
    POSITIVE LOGITS
     bandwidth
    0.08
     Filters
    0.08
    _filters
    0.08
    滤波åĻ¨
    0.08
    (Filter
    0.08
    (filters
    0.07
    Ctl
    0.07
     filtering
    0.07
    æ³¢çī¹
    0.07
    è¶ĬæĹ©
    0.07
    Activations Density 0.012%

    No Known Activations