© 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. 50952
    Prev
    Next
    INDEX
    Explanations

    genes or chromosomes

    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
    ãĤĦãģĭ
    -0.06
    oops
    -0.06
     s
    -0.06
     camb
    -0.05
    ä¼ĺçĤ¹æĺ¯
    -0.05
    ร
    -0.05
    /compiler
    -0.05
    âĨ
    -0.05
    èģªæĺİ
    -0.05
    åĴ¸å®ģ
    -0.05
    POSITIVE LOGITS
    osu
    0.08
    asian
    0.08
    inless
    0.08
     Again
    0.08
    assi
    0.08
    mixed
    0.08
     ÑģовмеÑģÑĤи
    0.08
    anyol
    0.08
    临åºĬåĮ»åѦ
    0.08
    ank
    0.08
    Activations Density 0.051%

    No Known Activations