© 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. 32082
    Prev
    Next
    INDEX
    Explanations

    special characters and operators

    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
     asym
    -0.07
    ×ŀש
    -0.06
    waran
    -0.06
     Enth
    -0.06
    æĹłçĸij
    -0.06
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.06
     adi
    -0.06
    èĥĮåIJİ
    -0.06
    ª
    -0.06
    æĽ´éķ¿
    -0.06
    POSITIVE LOGITS
     ве
    0.07
    ç¼Ī
    0.07
    å°Ĭæķ¬
    0.07
    evel
    0.07
    lesa
    0.07
    **|
    0.07
    çľĭçľĭåIJ§
    0.07
    ç±³å°Ķ
    0.07
    ìŀij
    0.07
    RIC
    0.07
    Activations Density 0.002%

    No Known Activations