© 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. 10663
    Prev
    Next
    INDEX
    Explanations

    Korean or East Asian names

    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
    ilha
    -0.07
    겪
    -0.07
    etje
    -0.07
    RenderingContext
    -0.07
    że
    -0.07
    isko
    -0.07
    ÙĦÙģ
    -0.07
    çĶ¨æ³ķ
    -0.07
    멤
    -0.07
    ServerError
    -0.07
    POSITIVE LOGITS
    ÑĬÑı
    0.07
    âĢij
    0.07
    âĢIJ
    0.07
    åªĽ
    0.06
    æĹ¥æŃ£å¼ı
    0.06
    ëŀĦ
    0.06
    IJ
    0.06
    -minded
    0.06
     boon
    0.06
    Ñģан
    0.06
    Activations Density 0.374%

    No Known Activations