© 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. 1619
    Prev
    Next
    INDEX
    Explanations

    numbers and listed variables

    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
    è¿Ļä¸ī个
    -0.16
    è¿Ļä¸īç§į
    -0.15
    è¿Ļä¸ī
    -0.14
     اÙĦØ«ÙĦاثة
    -0.14
    çļĦä¸ī个
    -0.14
    ä¸īæĿ¡
    -0.13
     ketiga
    -0.13
    ä¸ī个
    -0.13
    ä¸īåĢĭ
    -0.13
    ä¸ī人
    -0.13
    POSITIVE LOGITS
     dozens
    0.11
    listed
    0.10
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.10
     sixteen
    0.10
    List
    0.10
     eleven
    0.10
     numerous
    0.10
    åįģ个
    0.09
    åĩłåįģ个
    0.09
     zahlreichen
    0.09
    Activations Density 0.374%

    No Known Activations