© 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. 56333
    Prev
    Next
    INDEX
    Explanations

    coding or technical terms

    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
     Crossing
    -0.07
    ispers
    -0.07
    pp
    -0.07
     Gom
    -0.07
    inn
    -0.07
    енÑĮ
    -0.06
    åı¯æľĽ
    -0.06
    ä¿ĿæĬ¤ä½ľçĶ¨
    -0.06
    éĤ£æł·çļĦ
    -0.06
    ாவ
    -0.06
    POSITIVE LOGITS
    imson
    0.07
    ë§ĪìŀIJ
    0.07
    é¦ĸåħĪ
    0.07
    åºĶè¿IJ
    0.07
    ovsky
    0.07
    ĴĪ
    0.07
    çĻ¾äº¿
    0.07
    indre
    0.07
    æĥ³åĪ°
    0.07
    主ä½ĵçļĦ
    0.07
    Activations Density 0.001%

    No Known Activations