© 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. 43407
    Prev
    Next
    INDEX
    Explanations

    trigonometric angles and mathematical substitution

    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
    ç³»æķ°
    -0.08
     Richt
    -0.08
    å®ŀæĸ½äºĨ
    -0.08
    å®ŀæĸ½
    -0.07
    _avail
    -0.07
    åĴĮå®ŀæĸ½
    -0.07
     netto
    -0.07
    alk
    -0.07
    á»Ļt
    -0.07
    Ñĭл
    -0.07
    POSITIVE LOGITS
    -angle
    0.07
     corresponding
    0.06
     гÑĢадÑĥÑģ
    0.06
     Bez
    0.06
     angle
    0.06
     correspondant
    0.06
     زا
    0.06
     atan
    0.06
    æĶĴ
    0.06
     angles
    0.06
    Activations Density 0.002%

    No Known Activations