© 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. 51463
    Prev
    Next
    INDEX
    Explanations

    sender and recipient information

    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
    arra
    -0.08
    ì¼
    -0.07
    æ¯ĶåĪ«äºº
    -0.07
    åľı
    -0.07
    综治
    -0.06
    åįĬçĤ¹
    -0.06
    èijµèĬ±
    -0.06
    ì²ł
    -0.06
    ä¹±ä¸ĸ
    -0.06
    forth
    -0.06
    POSITIVE LOGITS
    /source
    0.08
    ูà¹ī
    0.08
    ç«Ļç«Ļ
    0.08
    åİ»åIJij
    0.08
     whom
    0.07
    /from
    0.07
    åĴĮ缮æłĩ
    0.07
    åľ°åĴĮ
    0.07
    iffe
    0.07
    /result
    0.07
    Activations Density 0.096%

    No Known Activations