© 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. 47997
    Prev
    Next
    INDEX
    Explanations

    mixture, compound, or blend

    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
    æ¯ı次
    -0.07
    æ¯ıæĿ¡
    -0.07
    ä¸ĢåĨį
    -0.07
    æ¯ıåŃ¦æľŁ
    -0.06
     recipro
    -0.06
    åİĨæĿ¥
    -0.06
    åħ³éĹŃçªĹåı£
    -0.06
    æ¯ıä¸ĢæŃ¥
    -0.06
    each
    -0.06
    roll
    -0.06
    POSITIVE LOGITS
    æ··åIJĪ
    0.10
     mixture
    0.10
    æ··åIJĪçī©
    0.09
     concentrations
    0.09
    åŃĺåľ¨äºİ
    0.09
     mixed
    0.09
    å°ijéĩı
    0.09
     mix
    0.09
    åħ±åŃĺ
    0.09
    大éĩıçļĦ
    0.08
    Activations Density 0.006%

    No Known Activations