© 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. 8500
    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
    adak
    -0.08
    宫å¤ĸ
    -0.08
    约èĢĮåIJĮ
    -0.08
    ä¾łä¼ł
    -0.08
    ures
    -0.07
    jac
    -0.07
    aing
    -0.07
    .iteritems
    -0.07
    ubb
    -0.07
    icale
    -0.07
    POSITIVE LOGITS
    èİĺ
    0.06
    KV
    0.06
    наÑĤ
    0.06
    èĭ¥ä¸į
    0.06
    edom
    0.06
    phu
    0.06
    astre
    0.06
    ä¸įæĶ¹
    0.06
    stocks
    0.06
    :
    0.06
    Activations Density 0.000%

    No Known Activations