© 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. 50303
    Prev
    Next
    INDEX
    Explanations

    instances, clusters, elements, fat, columns, plies, bras, addresses, donors

    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
    zul
    -0.09
    åľ°è¢«
    -0.07
    åĩ«
    -0.07
    ä¸İ交æµģ
    -0.07
    biz
    -0.07
    éĥ½åĴĮ
    -0.07
    nard
    -0.06
     /**<
    -0.06
     Xuyên
    -0.06
    ä¸Ģå¤ķ
    -0.06
    POSITIVE LOGITS
    èĢĮä¸įæĺ¯
    0.09
    instead
    0.08
    oston
    0.08
    ä¹ĭä¸Ĭ
    0.08
     rather
    0.08
    ä¹ĭä¸ĬçļĦ
    0.08
    дÑĢÑı
    0.08
    rather
    0.07
     geschieht
    0.07
    èĢĮéĿŀ
    0.07
    Activations Density 0.296%

    No Known Activations