© 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. 19666
    Prev
    Next
    INDEX
    Explanations

    Category

    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
    çĤ¹åĩ»ä¸Ĭæĸ¹èĵĿåŃĹ
    -0.09
    个人页
    -0.09
    订éĺħä¸ĵæłı
    -0.08
    θη
    -0.07
    é»į
    -0.07
    ç«¥åŃIJ
    -0.07
    <<<<<<<
    -0.07
    æīĭæľºç«Ļ
    -0.07
     pair
    -0.07
    饨
    -0.06
    POSITIVE LOGITS
    以ä¸ĬåĨħ容
    0.09
    ranken
    0.07
    çıŃä¸»ä»»å·¥ä½ľ
    0.07
    ioter
    0.07
    Å«k
    0.07
    大æĪIJ
    0.07
    References
    0.07
    è¿ĺæĥ³
    0.07
    dic
    0.07
    ãĤĪãģĭãģ£ãģŁ
    0.07
    Activations Density 0.220%

    No Known Activations