© 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. 31316
    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
    [email
    -0.08
    esel
    -0.07
    uppe
    -0.07
    ÙĪÙĨس
    -0.07
    ¦
    -0.07
    大ä¸ĵåıĬ以ä¸ĬåѦåİĨ
    -0.07
    enaar
    -0.07
    èĭĩ
    -0.07
    licated
    -0.07
    italia
    -0.07
    POSITIVE LOGITS
    å®īæİĴ
    0.08
    erd
    0.07
    aye
    0.07
    æĿij
    0.07
    çķª
    0.06
    涯
    0.06
    ä¸įå®ļ
    0.06
    ailles
    0.06
    ä¸Ģèµ·
    0.06
    ียà¸Ķ
    0.06
    Activations Density 0.000%

    No Known Activations