© 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. 64639
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with derivatives

    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
     sizes
    -0.08
    ä¸īåı£
    -0.07
    enumerator
    -0.07
    æł¸
    -0.07
     DN
    -0.07
    @student
    -0.07
    idon
    -0.07
    à¹īา
    -0.07
    occa
    -0.07
    ichten
    -0.07
    POSITIVE LOGITS
     symmetry
    0.07
    æĸ½æķĻ
    0.07
    åģı移
    0.07
    è½´çļĦ
    0.07
    åģı
    0.07
    ä¸Ģ鸣
    0.07
     bias
    0.07
     center
    0.07
    åģıåIJij
    0.07
    emasan
    0.07
    Activations Density 0.001%

    No Known Activations