© 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. 57103
    Prev
    Next
    INDEX
    Explanations

    date separators

    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¸įæį¢
    -0.08
    å°ı说ç½ij
    -0.07
    ero
    -0.07
    大æĪı
    -0.07
    xFB
    -0.07
    æĺ¯ä¸Ģç§įéĿŀ常
    -0.07
    nTo
    -0.07
    ERO
    -0.07
    人åķĬ
    -0.07
    é¾Ļå²Ĺ
    -0.07
    POSITIVE LOGITS
    bauer
    0.07
    æľīçļĦ
    0.07
    licit
    0.06
    ikka
    0.06
    åıij表æŶéĹ´
    0.06
    avar
    0.06
    èIJ©
    0.06
    ichel
    0.06
    ysel
    0.06
    berman
    0.06
    Activations Density 1.513%

    No Known Activations