© 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. 28590
    Prev
    Next
    INDEX
    Explanations

    cosine and sine functions

    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
    åľŃ
    -0.07
    tral
    -0.07
    Ïĥί
    -0.06
    åĪ¹
    -0.06
    èİ«æµĭ
    -0.06
     ger
    -0.06
    ied
    -0.06
     aval
    -0.06
    éĻĽ
    -0.06
     theat
    -0.06
    POSITIVE LOGITS
    ä¸įå¿ĺ
    0.08
    ners
    0.08
    occo
    0.08
    erving
    0.08
     Ãģlvarez
    0.07
    >|
    0.07
    ueur
    0.07
    رÙĪت
    0.07
    足以
    0.07
    èıģèĭ±
    0.07
    Activations Density 0.003%

    No Known Activations