© 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. 64418
    Prev
    Next
    INDEX
    Explanations

    names of organizations and official titles

    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
    нее
    -0.07
    å¹¼ç¨ļ
    -0.07
    GINE
    -0.07
    soever
    -0.06
    缴æİ¥æĪĸéĹ´æİ¥
    -0.06
    æĭĶæİī
    -0.06
    urada
    -0.06
    oglio
    -0.06
    åģļèµ·æĿ¥
    -0.06
    ä»Ģä¹Īéĥ½æ²¡æľī
    -0.06
    POSITIVE LOGITS
     ÙĪرئÙĬس
    0.09
     à¹ģละà¹Ģà¸Ľà¹ĩà¸Ļ
    0.08
    çļĦä¸Ģåijĺ
    0.07
    adora
    0.07
    ä¸İæĿİ
    0.07
     kiêm
    0.07
    reh
    0.07
    AndGet
    0.07
    anga
    0.07
     nonché
    0.07
    Activations Density 0.984%

    No Known Activations