© 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. 47968
    Prev
    Next
    INDEX
    Explanations

    Historic and heritage sites register

    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
    нÑĥÑģ
    -0.08
    åĨ°å±±
    -0.07
    è¯ķæİ¢
    -0.07
    engar
    -0.07
    uffled
    -0.07
    फल
    -0.07
    hatt
    -0.07
    åĨľåŀ¦
    -0.07
    ConnectionFactory
    -0.07
    ä¸ĢåĪĨ
    -0.07
    POSITIVE LOGITS
     heritage
    0.11
    ä¿ĿåŃĺ
    0.11
     preservation
    0.11
    æĸĩçī©
    0.10
     historic
    0.10
     ë³´ì¡´
    0.10
     UNESCO
    0.10
    åı¤è¿¹
    0.10
     preserving
    0.10
    ä¿ĿæĬ¤çļĦ
    0.10
    Activations Density 0.177%

    No Known Activations