© 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. 49024
    Prev
    Next
    INDEX
    Explanations

    abstract notation or matrices

    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
    ajara
    -0.07
    dock
    -0.07
    iefs
    -0.07
    unsch
    -0.07
    emoc
    -0.07
    abase
    -0.07
    åıįè¿ĩæĿ¥
    -0.07
    æł¹æį®èĩªèº«
    -0.07
    çıĬ
    -0.07
    ostas
    -0.07
    POSITIVE LOGITS
     notation
    0.09
    绣ä¸Ģ
    0.09
    æķ´é½IJ
    0.08
    绣ä¸ĢçļĦ
    0.08
    表达
    0.08
     succinct
    0.07
    ä¸Ģåı¥è¯Ŀ
    0.07
    缼
    0.07
     unify
    0.07
    æ¦Ĥæĭ¬
    0.07
    Activations Density 0.055%

    No Known Activations