© 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. 49652
    Prev
    Next
    INDEX
    Explanations

    group theory related terms

    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¸įéķ¿
    -0.07
    æĹłå°ĺ
    -0.07
    normalized
    -0.07
    веÑģ
    -0.07
    endig
    -0.07
     NASA
    -0.06
    è¶Ĭéķ¿
    -0.06
    nier
    -0.06
    çİĦå¹»å°ı说
    -0.06
    IGO
    -0.06
    POSITIVE LOGITS
    éļıçĿĢ社ä¼ļ
    0.08
    ĥĿ
    0.07
    yne
    0.07
    exe
    0.07
    两大
    0.07
     Tipp
    0.07
     chá»ijt
    0.07
    illot
    0.07
     permutation
    0.07
    zens
    0.07
    Activations Density 0.007%

    No Known Activations