© 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. 64746
    Prev
    Next
    INDEX
    Explanations

    subject of emails and documents

    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
    è¿Ļä¹Ī说
    -0.06
    lada
    -0.06
    Downloader
    -0.06
    个人æĪĸ
    -0.06
    обо
    -0.06
    æĥ³ä¸įåĪ°
    -0.06
    AMPLE
    -0.06
    çļĦ人åĴĮ
    -0.06
     Respons
    -0.06
    acias
    -0.06
    POSITIVE LOGITS
    åIJijä»ĸ们
    0.11
    ç»Ļä»ĸ们
    0.10
    ä»ĸ们çļĦ
    0.10
    让ä»ĸ们
    0.10
    å°Ĩä»ĸ们
    0.10
    è·Łä»ĸ们
    0.10
    åijĬè¯īä»ĸ们
    0.10
    Their
    0.10
     their
    0.10
    对ä»ĸ们çļĦ
    0.10
    Activations Density 0.419%

    No Known Activations