© 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. 57427
    Prev
    Next
    INDEX
    Explanations

    score and music

    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¨¡æł·
    -0.07
     append
    -0.06
    /framework
    -0.06
    append
    -0.06
    emers
    -0.06
    æĸ¹ä¾¿çļĦ
    -0.06
    å½ĵéĿ¢
    -0.06
    ège
    -0.06
    æĿĤ交
    -0.06
     troublesome
    -0.06
    POSITIVE LOGITS
    èIJ¥éĢłåĩº
    0.11
     mood
    0.09
    èIJ¥éĢłä¸Ģ个
    0.09
    ÑĢÑİ
    0.09
     choices
    0.09
    å¾Ĺå½ĵ
    0.09
    èī²è°ĥ
    0.09
    éĢīæĭ©åIJĪéĢĤçļĦ
    0.09
     подобÑĢ
    0.09
    èIJ¥éĢł
    0.09
    Activations Density 0.042%

    No Known Activations