© 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. 16873
    Prev
    Next
    INDEX
    Explanations

    trigonometric functions and math terms

    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
    管çIJĨæľīéĻIJåħ¬åı¸
    -0.07
    ستاÙĨÛĮ
    -0.07
    ç»Ĩ鼨
    -0.07
    à´¤àµį
    -0.07
    wijk
    -0.07
    ÑĪе
    -0.07
    æľĢæĸ°è¯Ħ论
    -0.07
    _sd
    -0.07
     ticking
    -0.06
    è¿Ļæĺ¯å¯¹
    -0.06
    POSITIVE LOGITS
    ansen
    0.08
    olem
    0.07
    isson
    0.07
    å·´å¡ŀ
    0.07
    iling
    0.06
    iler
    0.06
    æ°´çĶŁ
    0.06
     râ
    0.06
    ish
    0.06
     values
    0.06
    Activations Density 0.001%

    No Known Activations