© 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. 63175
    Prev
    Next
    INDEX
    Explanations

    trigonometry and angles

    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
    èĶ·
    -0.09
    åĻ©
    -0.09
    ä»İ天èĢĮéĻį
    -0.07
    éķ¿åĩº
    -0.07
    æĹ©é¤IJåIJİ
    -0.07
    çĿ¡çľłè´¨éĩı
    -0.07
    yyyyMMdd
    -0.07
    getline
    -0.07
    rael
    -0.07
    åĬ¨è¾Ħ
    -0.07
    POSITIVE LOGITS
    è§Ĵ度
    0.09
     trig
    0.08
    èµĭ
    0.08
     sin
    0.08
     angle
    0.08
     angles
    0.08
    ä¸īè§Ĵ
    0.08
    è§Ĵ
    0.08
     cosine
    0.08
    Angle
    0.08
    Activations Density 0.008%

    No Known Activations