© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46846
    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
    enho
    -0.07
    é³Į
    -0.07
    лÑĮÑģкий
    -0.07
    edir
    -0.06
    urio
    -0.06
    åĴĮç¾İ
    -0.06
    æ±Ģ
    -0.06
    ãĥ¬ãĥ³ãĤ¸
    -0.06
    urdy
    -0.06
     op
    -0.06
    POSITIVE LOGITS
     ÐŀÑģÑĤа
    0.07
    IDOS
    0.07
    å°ıé¢Ŀ
    0.07
    åIJĥå®Į
    0.06
    TimeInterval
    0.06
    è¦ģæ±ĤåѦçĶŁ
    0.06
    Õ¡Õ¾
    0.06
    astle
    0.06
    .finish
    0.06
    cum
    0.06
    Activations Density 0.000%

    No Known Activations