© 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. 48300
    Prev
    Next
    INDEX
    Explanations

    music or spoken word introducing content

    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
     tát
    -0.09
    ashian
    -0.08
    ebol
    -0.08
    itemap
    -0.08
    -uppercase
    -0.08
     หมวà¸Ķ
    -0.08
    å®ŀä½ĵç»ıæµİ
    -0.08
    çłĶä¿®çıŃ
    -0.08
    åĿIJæĭ¥
    -0.08
    åįİåĽ¾
    -0.08
    POSITIVE LOGITS
    :
    0.08
    ï¼ļ
    0.07
    0.07
    æľīåĽ°éļ¾
    0.07
    åĬłæ·±å¯¹
    0.07
    æľīæĿ¡ä»¶çļĦ
    0.07
    åĪ©çĶ¨
    0.06
    af
    0.06
    a
    0.06
    éĿĸ
    0.06
    Activations Density 0.001%

    No Known Activations