© 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. 21946
    Prev
    Next
    INDEX
    Explanations

    plot synopsis

    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
     aspir
    -0.07
    arani
    -0.07
    讳
    -0.07
    gues
    -0.07
    微信æī«ä¸Ģæī«
    -0.07
    æ²¾æŁĵ
    -0.07
    ashes
    -0.07
     ostr
    -0.07
    ä¸ĭåľº
    -0.06
    оÑĤов
    -0.06
    POSITIVE LOGITS
    éĢ»è¾ij
    0.14
     logic
    0.13
    主线
    0.12
    çļĦéĢ»è¾ij
    0.12
     Logic
    0.11
    éĤı輯
    0.11
     logique
    0.11
    èĦī绾
    0.11
    è¿ŀè´¯
    0.11
     mạch
    0.11
    Activations Density 0.039%

    No Known Activations