© 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. 60917
    Prev
    Next
    INDEX
    Explanations

    differential equations and marginal costs

    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
    oad
    -0.07
    èĩ¼
    -0.07
    APS
    -0.07
    è°Ĭ
    -0.06
    ä¹ĭé£İ
    -0.06
     Wich
    -0.06
    aign
    -0.06
    å¯ħ
    -0.06
     amator
    -0.06
    icity
    -0.06
    POSITIVE LOGITS
    æĪĸå°ı
    0.09
    Ń
    0.08
    สุà¸Ķ
    0.07
    Õ£
    0.07
    临
    0.07
    otropic
    0.07
    ôme
    0.07
    سÛĮ
    0.07
     dÃłng
    0.07
    å¾Īå°ı
    0.07
    Activations Density 0.005%

    No Known Activations