© 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. 8511
    Prev
    Next
    INDEX
    Explanations

    email signatures date stamps

    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
    ç§ijæĬĢè¿ĽæŃ¥
    -0.07
    æķ´é¡¿
    -0.07
    adie
    -0.07
    earn
    -0.06
    次æµıè§Ī
    -0.06
    æĬµ
    -0.06
    天æĺİ
    -0.06
     Tuch
    -0.06
    åĴĮæľįåĬ¡
    -0.06
     prest
    -0.06
    POSITIVE LOGITS
    неж
    0.07
    kung
    0.07
    éķľåŃIJ
    0.07
    mailto
    0.07
    åŃ©åŃIJçļĦæĪIJéķ¿
    0.07
    ocy
    0.07
    è¿Ķä¿¡
    0.07
     gracias
    0.06
    COMP
    0.06
    Kom
    0.06
    Activations Density 0.194%

    No Known Activations