© 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. 8664
    Prev
    Next
    INDEX
    Explanations

    excessive or abnormal growth/function

    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
    åIJīæĢĿ
    -0.07
    리ìłģìĿ¸
    -0.07
    inally
    -0.07
    sonian
    -0.07
    rible
    -0.07
    çģµæķı
    -0.07
    aruhi
    -0.07
    -rich
    -0.06
    ãĥĥãģ¨
    -0.06
    ìłģìĿ¸
    -0.06
    POSITIVE LOGITS
    าว
    0.08
    ignment
    0.08
    agment
    0.07
    inage
    0.07
    esy
    0.07
    uket
    0.07
    ljan
    0.07
    /bl
    0.07
    翻天
    0.07
    alisation
    0.07
    Activations Density 0.298%

    No Known Activations