© 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. 14245
    Prev
    Next
    INDEX
    Explanations

    compare

    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
    otra
    -0.09
    strup
    -0.08
    anguage
    -0.08
    fans
    -0.08
     Monta
    -0.08
     اÙĦÙģض
    -0.08
    á»ıng
    -0.08
    æķ°æį®ç»Łè®¡
    -0.07
    .wr
    -0.07
    æ±Ĥæĺ¯
    -0.07
    POSITIVE LOGITS
     nhau
    0.08
    å®īåħ¨æĢ§åĴĮ
    0.07
    åľ¨ä¸Ģèµ·çļĦ
    0.07
    aupt
    0.06
     between
    0.06
    åIJĦçıŃ
    0.06
    å½¼æѤçļĦ
    0.06
     дÑĢÑĥг
    0.06
    erras
    0.06
    毡
    0.06
    Activations Density 0.017%

    No Known Activations