© 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. 58002
    Prev
    Next
    INDEX
    Explanations

    logarithmic differentiation

    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
    åĦŁ
    -0.07
    åĸĭ
    -0.07
    º¼
    -0.07
    ä½Ļ次
    -0.07
     dziaÅĤ
    -0.06
    patr
    -0.06
    æŀ¶ä¸Ĭ
    -0.06
    æµģåĩº
    -0.06
    ç»ıå®¡æŁ¥
    -0.06
    дейÑģÑĤви
    -0.06
    POSITIVE LOGITS
     derivatives
    0.09
     derivative
    0.08
    veli
    0.08
     differentiation
    0.07
    jal
    0.07
     differentiate
    0.07
     differentiated
    0.07
    éĩįåĨĻ
    0.07
    æıIJ
    0.07
    ãĥĢãĥ¼
    0.07
    Activations Density 0.033%

    No Known Activations