© 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. 64077
    Prev
    Next
    INDEX
    Explanations

    anomalies, algebra, App, paradoxical, leaks

    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
    ODO
    -0.07
    æĮ¨
    -0.07
    &r
    -0.07
    getattr
    -0.06
    ete
    -0.06
    tex
    -0.06
    onyme
    -0.06
    tire
    -0.06
     distanci
    -0.06
    çĭ¬èµĦ
    -0.06
    POSITIVE LOGITS
    unen
    0.08
     Cliff
    0.08
    riad
    0.07
    eku
    0.07
    åºĩ
    0.07
    åĬĪ
    0.07
     اÙĦÙħØ·
    0.07
    ä¸Ģ女
    0.07
    ä½
    0.07
    ä¿ĿæĬ¤çļĦ
    0.07
    Activations Density 0.001%

    No Known Activations