© 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. 3578
    Prev
    Next
    INDEX
    Explanations

    filing applications and submission

    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
    æµģéĢĿ
    -0.07
    ulia
    -0.06
    iose
    -0.06
    ÙĬا
    -0.06
    åĨį继ç»Ń
    -0.06
    apon
    -0.06
    à¸ŀย
    -0.06
    æĽ´æĸ°æĹ¥æľŁ
    -0.06
    æĦıè§ģåıįé¦Ī
    -0.06
    æľīæĿĥä¿ĿçķĻ
    -0.06
    POSITIVE LOGITS
     diajukan
    0.09
     submission
    0.09
     submitted
    0.09
    æĦıåIJij
    0.09
    /request
    0.08
    并æıIJ交
    0.08
     Submission
    0.08
    书çļĦ
    0.08
    åıĹçIJĨ
    0.08
    书ä¸Ń
    0.08
    Activations Density 0.195%

    No Known Activations