© 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. 27992
    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
    tale
    -0.07
    itore
    -0.07
    ä¹IJä¹İ
    -0.07
    ç¯ĩä¸Ģ
    -0.07
    ÑĤков
    -0.07
     Tik
    -0.07
    åĴĮè§ĦèĮĥ
    -0.06
    èĢĮçŁ¥
    -0.06
    åıĬ家éķ¿
    -0.06
    taler
    -0.06
    POSITIVE LOGITS
    缩åĨĻ
    0.07
    °
    0.07
    Markup
    0.07
    éķ¿ç©º
    0.07
    upes
    0.07
    orton
    0.06
    jak
    0.06
    满
    0.06
    æł·çļĦ
    0.06
    ortes
    0.06
    Activations Density 0.000%

    No Known Activations