© 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. 33055
    Prev
    Next
    INDEX
    Explanations

    filled to overflowing

    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
     aisl
    -0.07
    éĽĨä¸Ń
    -0.07
    蹤
    -0.07
     ÙħجÙħ
    -0.07
     separat
    -0.07
    æ±ĩ
    -0.07
    éļĶ离
    -0.07
    åįķçĭ¬çļĦ
    -0.07
     оÑĤделÑĮ
    -0.07
    èĤ¤è´¨
    -0.07
    POSITIVE LOGITS
    满äºĨ
    0.18
    填满
    0.18
     filling
    0.17
    fill
    0.16
     filled
    0.15
     penuh
    0.15
    /full
    0.15
    饱满
    0.15
    -fill
    0.15
    filled
    0.14
    Activations Density 0.095%

    No Known Activations