© 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. 64362
    Prev
    Next
    INDEX
    Explanations

    malalignment, orthodontics, lesions, thick

    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
    ä¸įæ¼ı
    -0.07
    ific
    -0.07
     courts
    -0.07
    punt
    -0.06
     Interested
    -0.06
    lom
    -0.06
    åīįå¾Į
    -0.06
    RenderingContext
    -0.06
    æĸ¯åŁº
    -0.06
     пиÑĢо
    -0.06
    POSITIVE LOGITS
    çİ°çĬ¶
    0.10
    缮æłĩæĺ¯
    0.09
    缮æłĩ
    0.09
    ä¸ºçĽ®æłĩ
    0.08
    åĴĮ缮æłĩ
    0.08
    çļĦ缮æłĩ
    0.08
    缮æłĩåĴĮ
    0.08
     targeted
    0.08
    æĦ¿æĻ¯
    0.08
    üge
    0.08
    Activations Density 0.008%

    No Known Activations