© 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. 62885
    Prev
    Next
    INDEX
    Explanations

    measure theory concepts

    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
    æĶ»
    -0.07
    ãģĭãģĦ
    -0.07
    tep
    -0.07
    vors
    -0.07
    repub
    -0.07
    kla
    -0.06
    ÐIJÐŀ
    -0.06
    anlı
    -0.06
    å¢ĥåľ°
    -0.06
    _ONLY
    -0.06
    POSITIVE LOGITS
     density
    0.08
     densities
    0.08
    æµģéĢĿ
    0.08
    æµģæ·Į
    0.07
    æ½į
    0.07
    ehm
    0.07
    æµģåĩº
    0.07
    éĩı
    0.07
    æµģåħ¥
    0.07
     Density
    0.07
    Activations Density 0.005%

    No Known Activations