© 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. 20653
    Prev
    Next
    INDEX
    Explanations

    exclude or referring

    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
    _dat
    -0.08
    _fatal
    -0.08
    aÄĩ
    -0.07
    enson
    -0.07
    寡
    -0.07
    æĶ¾é¡Į
    -0.07
    yadi
    -0.07
    ä¸İåħ±
    -0.07
    ä¸Ģå¦Ĥ
    -0.07
    缴æݥ影åĵįåĪ°
    -0.07
    POSITIVE LOGITS
     excludes
    0.09
     exclude
    0.09
    æİĴéĻ¤
    0.08
     excluded
    0.08
     excluding
    0.08
    åı¸
    0.08
    ä¸įåĮħæĭ¬
    0.07
    etas
    0.07
     Exclude
    0.07
    éģ¿åħį
    0.07
    Activations Density 0.005%

    No Known Activations