© 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. 33262
    Prev
    Next
    INDEX
    Explanations

    describing properties or features

    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
     invece
    -0.07
    çļĦä¸įåIJĮ
    -0.07
     okazji
    -0.07
    instead
    -0.07
     instead
    -0.07
     ÑģÑĢоÑĩно
    -0.07
    以åıĬåħ¶ä»ĸ
    -0.07
    pei
    -0.07
    è¾ĥ为
    -0.07
    ä¸įäºĨçļĦ
    -0.07
    POSITIVE LOGITS
     both
    0.07
    ä¸Ķ
    0.07
    以èĩ³äºİ
    0.07
    ä¸Ķåľ¨
    0.07
    ãģ¾ãģ¾ãģ§
    0.07
     regards
    0.07
    criptor
    0.07
    /by
    0.06
     ÙĪغÙĬر
    0.06
    ä¸Ķåħ·æľī
    0.06
    Activations Density 0.439%

    No Known Activations