© 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. 62669
    Prev
    Next
    INDEX
    Explanations

    periodic phenomena, functions, and data

    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
    atorium
    -0.09
    zioni
    -0.09
    fér
    -0.08
    两åİħ
    -0.08
    çīĮçļĦ
    -0.08
    Åijl
    -0.08
    为好åıĭ
    -0.08
     Lone
    -0.08
    olk
    -0.08
    .fm
    -0.08
    POSITIVE LOGITS
    ity
    0.11
    æĢ§çļĦ
    0.08
    æĢ§å¼º
    0.08
    æĢ§åıĬ
    0.08
    æĢ§å¥½
    0.08
    æĢ§
    0.07
    æĢ§ä¸İ
    0.07
    incinn
    0.07
    n
    0.07
    ÑģÑı
    0.07
    Activations Density 0.004%

    No Known Activations