© 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. 22619
    Prev
    Next
    INDEX
    Explanations

    acronyms and symbols

    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
    wald
    -0.07
    Č↵
    -0.07
    eces
    -0.07
    agnol
    -0.07
    æĿĥ
    -0.07
    TCHA
    -0.07
    apesh
    -0.07
     اÙĦغÙĬر
    -0.07
     ÙĦÙĪا
    -0.07
    println
    -0.07
    POSITIVE LOGITS
    é¦ĸåħĪæĺ¯
    0.08
    odore
    0.07
    åĪĨåĪ¥æĺ¯
    0.07
    åĪĨåĪ«æĺ¯
    0.07
    ²
    0.07
     ugyanis
    0.07
    åIJĮæł·æĺ¯
    0.06
    abis
    0.06
    Ö°
    0.06
     âŀ
    0.06
    Activations Density 1.132%

    No Known Activations