© 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. 55499
    Prev
    Next
    INDEX
    Explanations

    George W. Bush, Sarah Palin, Geronimo

    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
    丽èİİ
    -0.08
    æľĪçĶŁ
    -0.07
    á»ķi
    -0.07
     Leban
    -0.07
    ushman
    -0.07
    åħŃçĻ¾
    -0.07
    ä¾Ŀä¾Ŀ
    -0.07
    vain
    -0.07
    ç»ķ
    -0.07
    çİ¥
    -0.07
    POSITIVE LOGITS
    é¦ĸ度
    0.07
    ansch
    0.07
     ensuing
    0.07
    çŃĶå¤į
    0.07
    åį·çĥŁ
    0.06
    æĦŁæĥ³
    0.06
    ARGV
    0.06
    æŁ¥æĶ¶
    0.06
    èĩº
    0.06
     urs
    0.06
    Activations Density 0.462%

    No Known Activations