© 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. 57891
    Prev
    Next
    INDEX
    Explanations

    sports terms

    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
     ined
    -0.07
    æīĢæľī
    -0.07
    fore
    -0.06
    Wr
    -0.06
    æŀĿ
    -0.06
    éģµä»İ
    -0.06
     breath
    -0.06
    缸
    -0.06
    æ±ŀ
    -0.06
    æѤ
    -0.06
    POSITIVE LOGITS
    ipse
    0.09
    ajar
    0.09
    å·²è¿ĩ
    0.09
    ĥĿ
    0.09
    usual
    0.08
    å·²ç»ıè¿ĩåİ»
    0.08
    çīĪæĿĥå½ĴåİŁä½ľèĢħ
    0.08
    _userid
    0.08
    ä¸ĢèĪ¬æĺ¯
    0.08
    ,default
    0.08
    Activations Density 0.001%

    No Known Activations