© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2544
    Prev
    Next
    INDEX
    Explanations

    completeness and closed sets

    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
    asten
    -0.08
    ä¸įäºī
    -0.07
    ạt
    -0.07
    ToMany
    -0.07
    λÎŃ
    -0.07
    .Params
    -0.07
    åİħ
    -0.07
     ÙĪاÙĦÙĦÙĩ
    -0.07
    ×Ļס
    -0.07
    æĸĩéĿĻ
    -0.07
    POSITIVE LOGITS
    å®Įå¤ĩ
    0.08
    æŁ¥æ¼ı补缺
    0.08
    è¡¥é½IJ
    0.08
    olti
    0.07
     completeness
    0.07
    å®ĮåĸĦ
    0.07
    æŁ¥æ¼ı
    0.07
    延
    0.07
    agnet
    0.07
     Authority
    0.07
    Activations Density 0.003%

    No Known Activations