© 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. 31465
    Prev
    Next
    INDEX
    Explanations

    during the earliest case

    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
     thereof
    -0.09
    å·¥ä½ľè¿Ľè¡ĮäºĨ
    -0.09
     meanwhile
    -0.08
    æĥħåĨµè¿Ľè¡ĮäºĨ
    -0.08
     daarvan
    -0.08
    æĪĸå°ij
    -0.08
    ',(
    -0.08
    åıĸèĢĮ代ä¹ĭ
    -0.08
    大åIJī
    -0.08
    بارÙĩ
    -0.08
    POSITIVE LOGITS
     tersendiri
    0.07
    onne
    0.07
    ä¸įèĥľ
    0.06
    ãģ«éĻIJ
    0.06
     sight
    0.06
     ÙĪÙĬÙħÙĥÙĨ
    0.06
    ãģ£ãģ¦ãģĬãĤĬ
    0.06
    ä¸įå°ijçļĦ
    0.06
    ìľ¼ë¡ľëıĦ
    0.06
    ino
    0.06
    Activations Density 0.530%

    No Known Activations