© 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. 7738
    Prev
    Next
    INDEX
    Explanations

    sports competition athletes

    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
     separately
    -0.06
    ãģ¡ãģ«
    -0.06
    ward
    -0.06
    uti
    -0.06
    èĤīçľ¼
    -0.06
    éĩİå¿ĥ
    -0.06
    çݯæ¯Ķ
    -0.06
    wards
    -0.06
    å¸ĮæľĽåı¯ä»¥å¸®åĬ©
    -0.06
    ìĦł
    -0.06
    POSITIVE LOGITS
    æĦıåij³
    0.08
    éĸ²
    0.08
    ä¸İä¼łç»Ł
    0.08
    à¸ĺร
    0.07
     TÆ°á»Łng
    0.07
    对åı£
    0.07
    adt
    0.07
    模æĭŁ
    0.07
    loh
    0.07
    illac
    0.07
    Activations Density 0.001%

    No Known Activations