© 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. 38284
    Prev
    Next
    INDEX
    Explanations

    is called

    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¸ĢæĪIJ
    -0.09
    æĺ¯ä¸Ģ大
    -0.07
    åĽī
    -0.07
    ä¸Ģå¾ĭ
    -0.07
    ¾
    -0.07
    顾åIJįæĢĿ
    -0.07
    vene
    -0.07
    vir
    -0.07
    eg
    -0.07
    æ¯Ķå¦Ĥ说
    -0.07
    POSITIVE LOGITS
    åħ¸åŀĭçļĦ
    0.08
     tzw
    0.08
    å±ŀäºİ
    0.08
    ç»ıåħ¸çļĦ
    0.08
     tzv
    0.08
     sogenannte
    0.07
     sogenannten
    0.07
     classic
    0.07
    ä½ĵçİ°äºĨ
    0.07
     reminiscent
    0.07
    Activations Density 0.074%

    No Known Activations