© 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. 64823
    Prev
    Next
    INDEX
    Explanations

    cell-to-cell or B-cell-mediated

    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
    aranya
    -0.10
    toa
    -0.09
    ÙĥÙĬر
    -0.09
    éĩįçĤ¹æĺ¯
    -0.08
    缮æłĩæĺ¯
    -0.08
    gång
    -0.08
    arana
    -0.08
    ä¹Łå°±ä¸į
    -0.08
    zac
    -0.08
    Äħtek
    -0.08
    POSITIVE LOGITS
    çļĦä¸Ģç§į
    0.12
    ä¸ŃçļĦä¸Ģç§į
    0.09
    çļĦä¸Ģ種
    0.08
    ä»Ģä¹ĪçļĦ
    0.08
    çļĦä¸Ģç§įæĸ¹å¼ı
    0.07
    èĢĮéĿŀ
    0.07
    åľ¨ä¸Ģå®ļ
    0.07
    çļĦä¸Ģ项éĩįè¦ģ
    0.07
    æŁIJç§į
    0.06
     **
    0.06
    Activations Density 0.018%

    No Known Activations