© 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. 40524
    Prev
    Next
    INDEX
    Explanations

    alpha, a, x, S, age

    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
    vik
    -0.07
    umn
    -0.07
    ä¸Ńåįİæ°ijæĹıçļĦ
    -0.06
    _PLACE
    -0.06
    PELL
    -0.06
    åĽ
    -0.06
    lov
    -0.06
    -IN
    -0.06
    amp
    -0.06
    éĨį
    -0.06
    POSITIVE LOGITS
    èī²åĪĹ
    0.08
    人为
    0.08
    ä¸īä¼ļ
    0.08
    uhe
    0.08
    fans
    0.07
    æĪijåIJĹ
    0.07
    cleo
    0.07
    ç²īä¸Ŀ们
    0.07
    kı
    0.07
    Formatter
    0.07
    Activations Density 0.118%

    No Known Activations