© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14612
    Prev
    Next
    INDEX
    Explanations

    sorting algorithm contexts

    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
    woch
    -0.07
    ilea
    -0.07
    еÑĪе
    -0.06
    eker
    -0.06
    ederland
    -0.06
    濯
    -0.06
    åıĪæĪĸèĢħ
    -0.06
    -ves
    -0.06
    ä¿¡çļĦ
    -0.06
    éºĵ
    -0.06
    POSITIVE LOGITS
    pedia
    0.08
    家æĿij
    0.07
    两个åŃĹ
    0.07
    zens
    0.07
    unger
    0.07
    æ°ı
    0.07
    oner
    0.07
    åĬŀ主任
    0.07
    ouis
    0.06
    ij¸
    0.06
    Activations Density 0.402%

    No Known Activations