© 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. 32256
    Prev
    Next
    INDEX
    Explanations

    volume or volumes

    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
    ä¸Ĭä¸ĢæĿ¡
    -0.08
    纸æĿ¡
    -0.08
    ä¸Ģæ´¾
    -0.07
    apai
    -0.07
    åħ¨èº«çļĦ
    -0.07
    éĺ²èĮĥæĦıè¯Ĩ
    -0.07
    PY
    -0.07
    פ×ĺ
    -0.07
    ienza
    -0.07
    ä¸ĢæĭĽ
    -0.07
    POSITIVE LOGITS
    contains
    0.08
    åĨĮ
    0.07
     contenant
    0.07
    covering
    0.07
    covers
    0.07
    第ä¸īæľŁ
    0.07
    çij°
    0.06
    ÑĸÑĢ
    0.06
    iment
    0.06
    меÑģÑĤи
    0.06
    Activations Density 0.028%

    No Known Activations