© 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. 9711
    Prev
    Next
    INDEX
    Explanations

    file path and markdown headings

    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
    æĢ§ä»¥åıĬ
    -0.08
    æĺ¯ä»Ģä¹ĪæĦıæĢĿ
    -0.07
    acce
    -0.07
    çļĦæĺ¯ä»Ģä¹Ī
    -0.07
    家å®Ŀ
    -0.07
     vÃŃt
    -0.07
    æĢ§åĴĮ
    -0.07
    elf
    -0.07
    ä»»ä½ķåªĴä½ĵ
    -0.07
    oui
    -0.07
    POSITIVE LOGITS
    cee
    0.08
    ãĢĤ
    0.08
     compreh
    0.07
     kinds
    0.07
    kind
    0.07
    o
    0.06
    .
    0.06
    riff
    0.06
    į
    0.06
    ãĢĤ.
    0.06
    Activations Density 0.001%

    No Known Activations