© 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. 34147
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and symbols

    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
     prê
    -0.08
    Globals
    -0.08
    elsing
    -0.08
    ÑĤали
    -0.08
    arau
    -0.08
    mente
    -0.07
    åĪ©çļĦ
    -0.07
    STALL
    -0.07
    heimer
    -0.07
    TING
    -0.07
    POSITIVE LOGITS
    ä¹ĭ以
    0.07
    Fans
    0.06
    าà¸Ī
    0.06
    ãĢĤ)
    0.06
     terms
    0.06
    avigate
    0.06
    æ¶ī
    0.06
    ł
    0.06
    à¸Ĺาà¸ĩà¸ģาร
    0.06
    aven
    0.06
    Activations Density 0.003%

    No Known Activations