© 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. 50038
    Prev
    Next
    INDEX
    Explanations

    biological or technical modifiers

    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´»åĬ¨åĴĮ
    -0.09
    å¸ĥå±ĢåĴĮ
    -0.08
    ä¸ĵ家åĴĮ
    -0.08
    пÑĢоÑĩем
    -0.08
    ogat
    -0.08
    å±ŀæĢ§åĴĮ
    -0.08
    æĬ¥åijĬåĴĮ
    -0.08
    æĦıè¯ĨåĴĮ
    -0.07
    ä»»åĬ¡åĴĮ
    -0.07
    åįİ西
    -0.07
    POSITIVE LOGITS
    ape
    0.08
    isable
    0.07
    /or
    0.07
    mts
    0.06
    ãģĭãģ¤
    0.06
     olmayan
    0.06
    à¸Ĥวัà¸į
    0.06
    ç»Ĩ鼨
    0.06
    ettava
    0.06
     nature
    0.06
    Activations Density 0.319%

    No Known Activations