© 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. 21768
    Prev
    Next
    INDEX
    Explanations

    numbers and ranges

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    볨
    -0.07
    jiang
    -0.07
    åŁ¹è®ŃçļĦ
    -0.07
    绣称
    -0.07
    ynn
    -0.07
    æĻ¯åĮºåĨħ
    -0.07
    arring
    -0.07
    ãģĹãģĮ
    -0.07
     overarching
    -0.06
    alla
    -0.06
    POSITIVE LOGITS
    è¡¢
    0.07
    端
    0.07
    ặng
    0.06
    ÑĨионеÑĢ
    0.06
    оÑģÑĤа
    0.06
    æł¼ä¸½
    0.06
     muted
    0.06
    è¡Ģä¸Ŀ
    0.06
     Malone
    0.06
    ç«¿
    0.06
    Activations Density 0.013%

    No Known Activations