© 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. 21627
    Prev
    Next
    INDEX
    Explanations

    stadium and seating related words

    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
    æįı
    -0.07
    Branch
    -0.07
    /Branch
    -0.07
     branch
    -0.07
    èµ°åľ¨
    -0.07
    /thumb
    -0.07
     branche
    -0.07
    åĨĽä¸Ń
    -0.07
    表çİ°åĩº
    -0.07
     Branch
    -0.07
    POSITIVE LOGITS
     seating
    0.10
    è§Ĥä¼Ĺ
    0.10
    ä¸Ń央
    0.09
    纵深
    0.09
    å¸ĥç½®
    0.09
     seats
    0.09
     khán
    0.09
    è§Ģçľ¾
    0.08
     audience
    0.08
    座ä½į
    0.08
    Activations Density 0.068%

    No Known Activations