© 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. 24668
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ä»İä½ķ
    -0.07
    ä¸Ģ度çļĦ
    -0.07
    .standard
    -0.07
     ëĪĦ
    -0.06
    mins
    -0.06
    à¸ģะ
    -0.06
    igd
    -0.06
    ambe
    -0.06
    æľ¬é¡µ
    -0.06
    )":
    -0.06
    POSITIVE LOGITS
    olving
    0.08
    hec
    0.08
    olog
    0.07
    ieten
    0.07
    hofer
    0.07
    orean
    0.07
    hren
    0.07
    é¾ĻèĻİ
    0.07
    heu
    0.07
    éħĴåIJİ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.