© 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. 12597
    Prev
    Next
    INDEX
    Explanations

    telling or saying something

    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
    кали
    -0.08
    cion
    -0.08
    æĿ¥ä¸ª
    -0.07
     Tulis
    -0.07
    culp
    -0.07
    åij¼åĴĮ
    -0.07
     scopes
    -0.07
    mlin
    -0.07
    ãģķãģĻãģĮ
    -0.07
    ä¹ĭéģ¥
    -0.07
    POSITIVE LOGITS
     Ru
    0.07
     [
    0.07
    åĪĽéĢłçļĦ
    0.07
    ä¼Łå¤§çļĦ
    0.06
    ä¼Łå¤§
    0.06
    çļĦä¼Łå¤§
    0.06
     pec
    0.06
    ype
    0.06
    pecies
    0.06
    [a
    0.06
    Activations Density 0.332%

    No Known Activations