© 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. 64781
    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
    mdl
    -0.08
    olge
    -0.08
    .origin
    -0.08
    ivelmente
    -0.08
    idot
    -0.08
    é¦ĸéĥ¨
    -0.08
    aland
    -0.08
    ibile
    -0.07
    æ²³æ¹ĸ
    -0.07
    ä¸įåIJĮç¨ĭ度çļĦ
    -0.07
    POSITIVE LOGITS
    adar
    0.06
    agli
    0.06
    uur
    0.06
    æĪijäºĨ
    0.06
    uty
    0.06
    remote
    0.06
    orem
    0.06
     Mitt
    0.06
    osis
    0.06
    æĢ§è´¨çļĦ
    0.06
    Activations Density 0.000%

    No Known Activations