© 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. 20883
    Prev
    Next
    INDEX
    Explanations

    polymomials, vectors, matrix math

    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
    æĸĩç«łæĿ¥æºIJ
    -0.08
    ovil
    -0.08
    è¿Ļ份
    -0.07
    å®ģ
    -0.07
    TAIL
    -0.07
    ä¸ŃçĶŁ
    -0.07
    çİĦå¾·
    -0.07
    неж
    -0.07
    ÄĻg
    -0.07
    ellow
    -0.07
    POSITIVE LOGITS
     suspend
    0.07
     Ran
    0.06
    orra
    0.06
     Raz
    0.06
    apon
    0.06
     Dam
    0.06
     rá
    0.05
    ä¸īå¹´åīį
    0.05
     abst
    0.05
    大åIJī
    0.05
    Activations Density 0.191%

    No Known Activations