© 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. 45978
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation followed by identifiers

    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
    æīİ
    -0.08
    /arm
    -0.07
    KY
    -0.07
    à¸łà¸±
    -0.07
    å¸Ĥ人æ°ijæĶ¿åºľ
    -0.07
    ä¸Ĭä¸Ģå±Ĥ
    -0.06
    ↵   ↵
    -0.06
    ļ
    -0.06
    ä¼ı
    -0.06
    ä¸Ĭä¸Ģå±Ĥ楼
    -0.06
    POSITIVE LOGITS
    çĻ¾æĪĺ
    0.08
    ulte
    0.07
    oble
    0.07
    缮ä¸Ń
    0.07
    è¾ĥéĩį
    0.07
    onte
    0.07
    ãģªãģĦãģ®ãģ§
    0.06
    istos
    0.06
    çĻ¾è®¡
    0.06
    inker
    0.06
    Activations Density 0.038%

    No Known Activations