© 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. 31376
    Prev
    Next
    INDEX
    Explanations

    spam, excuses, holiday, test

    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
     tan
    -0.08
    延年
    -0.07
     thôi
    -0.07
    ume
    -0.06
     electro
    -0.06
    ouch
    -0.06
    rint
    -0.06
    lv
    -0.06
    eled
    -0.06
    uccio
    -0.06
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.10
    æĽ´ä¸įæĺ¯
    0.09
    åį´è¿ĺæĺ¯
    0.09
    èĢĮæĺ¯ä¸Ģç§į
    0.09
    ä¹Łä¸įçĶ¨
    0.08
    èĢĮæĺ¯è¦ģ
    0.08
    ä½Ĩåį´
    0.08
    åį´èĥ½
    0.08
     berlebihan
    0.08
    èĢĮæĺ¯åľ¨
    0.08
    Activations Density 0.070%

    No Known Activations