© 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. 55681
    Prev
    Next
    INDEX
    Explanations

    percentage value

    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
    åĿļæĮģ
    -0.07
    ì²ĺ
    -0.07
    æ·ĩ
    -0.07
     homophobic
    -0.07
    æĻ®
    -0.07
     unreachable
    -0.06
    åIJĮæĹ¥
    -0.06
    温
    -0.06
     Robinson
    -0.06
    rate
    -0.06
    POSITIVE LOGITS
    æķ°éĩı为
    0.08
    对äºİä¸Ģ个
    0.08
    ulia
    0.08
     sejumlah
    0.07
    åľ¨æīĢ
    0.07
    æķ°éĩıåĴĮ
    0.07
    iben
    0.07
    asca
    0.07
    対象
    0.07
    大æī¹
    0.07
    Activations Density 0.549%

    No Known Activations