© 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. 42848
    Prev
    Next
    INDEX
    Explanations

    letters and correspondence

    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
    æľ¬ç«ĻåĨħ容
    -0.07
    对æѤä¸įæī¿æĭħä»»ä½ķ
    -0.07
     Trit
    -0.07
    oplevel
    -0.07
    åı£èħĶ
    -0.06
    éĢ£ãĤĮãģ¦
    -0.06
    é¼ĵæİĮ
    -0.06
    讲解
    -0.06
    åı£è¯Ģ
    -0.06
    /licenses
    -0.06
    POSITIVE LOGITS
    ä¸Ģå°ģ
    0.16
     letters
    0.12
     пиÑģÑĮмо
    0.12
     gá»Ńi
    0.12
    /email
    0.12
     пиÑģÑĮма
    0.12
     letter
    0.12
    信件
    0.11
    à¸īà¸ļัà¸ļ
    0.11
     addressed
    0.11
    Activations Density 0.367%

    No Known Activations