© 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. 26240
    Prev
    Next
    INDEX
    Explanations

    water transport

    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
    常éĿĴ
    -0.09
    èĸ°
    -0.08
    emade
    -0.08
    累累
    -0.08
    æ¸Ĭ
    -0.07
    æľīèī²éĩijå±ŀ
    -0.07
    油管
    -0.07
    گاÙĩ
    -0.07
     вÑĭÑģÑĤав
    -0.07
    UTE
    -0.07
    POSITIVE LOGITS
    änz
    0.07
    melon
    0.07
    ForKey
    0.06
    åIJĮä¸ļ
    0.06
    -dominated
    0.06
    anteil
    0.06
    çī¹å°Ķ
    0.06
    çıł
    0.06
     sob
    0.06
    mma
    0.06
    Activations Density 0.013%

    No Known Activations