© 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. 12913
    Prev
    Next
    INDEX
    Explanations

    list items, selections, or phrases

    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
     Appel
    -0.07
    upas
    -0.07
    urence
    -0.07
    onical
    -0.07
    anean
    -0.06
    icia
    -0.06
    ikin
    -0.06
     theres
    -0.06
    éģ¥
    -0.06
    ulan
    -0.06
    POSITIVE LOGITS
    åŃ¦ä¹łè®¡åĪĴ
    0.07
    minent
    0.07
    chow
    0.07
    çĬ
    0.07
    ket
    0.07
    纳æĸ¯
    0.07
    人åİ»
    0.06
     ÙħÙĨد
    0.06
     Prod
    0.06
    çĬ¯
    0.06
    Activations Density 0.087%

    No Known Activations