© 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. 50988
    Prev
    Next
    INDEX
    Explanations

    constant temperature or controlled variables

    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
    åĴĮä»ĸ们
    -0.07
    ä¸İä»ĸ们
    -0.07
    tese
    -0.07
    подоб
    -0.06
    ç©¿ä¸ĬäºĨ
    -0.06
    缴æİ¥ä¸İ
    -0.06
    ulette
    -0.06
    اÙĦÛĮ
    -0.06
    èĩªæĿ¥
    -0.06
    éĻĢ
    -0.06
    POSITIVE LOGITS
    ä¸įè®Ĭ
    0.09
    ä¸įåıĺçļĦ
    0.09
    ä¸įåıĺ
    0.08
    lined
    0.08
    ä¸įæĶ¾
    0.08
    æģĴå®ļ
    0.08
    稳ä½ı
    0.07
    ä¿ĿæĮģä¸įåıĺ
    0.07
     constant
    0.07
    ä½ı
    0.07
    Activations Density 0.006%

    No Known Activations