© 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. 50630
    Prev
    Next
    INDEX
    Explanations

    http:// or URLs

    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
    ä¸ĢçĽ´åľ¨
    -0.08
    å»ĸ
    -0.07
    çļĦè¯Ŀ
    -0.07
    .Empty
    -0.07
    æ£Ģ
    -0.07
    å¿
    -0.06
    æ²Ļ
    -0.06
    æĭĸ
    -0.06
    eka
    -0.06
    gn
    -0.06
    POSITIVE LOGITS
    kap
    0.08
    levant
    0.08
    .rar
    0.07
    utnik
    0.07
    åı¤éĥ½
    0.07
     infatti
    0.07
     indeed
    0.07
     кÑģÑĤаÑĤи
    0.07
     اÙĦرØŃ
    0.07
    ertype
    0.07
    Activations Density 0.003%

    No Known Activations