© 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. 9889
    Prev
    Next
    INDEX
    Explanations

    important/desirable/common followed by a noun

    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
    agi
    -0.09
    åijĹ
    -0.09
    quests
    -0.09
    utip
    -0.08
    诸å¦Ĥ
    -0.08
    çļĦ人æĺ¯
    -0.08
    çļĦæ°ĶåĬ¿
    -0.08
    ä¹ĭä¸ĢçļĦ
    -0.08
    å¦Ĥä¸ĭ
    -0.08
    ãĥįãĥ«
    -0.08
    POSITIVE LOGITS
    åĽŀäºĭ
    0.09
    ç»ĦæĪIJéĥ¨åĪĨ
    0.09
     Bestandteil
    0.08
    ä¸Ķ
    0.08
    èĢĮä¸Ķæĺ¯
    0.08
     contributor
    0.08
    èĢĮä¸Ķ
    0.07
     geweest
    0.07
    èĢĮä¸Ķæľī
    0.07
     phenomenon
    0.07
    Activations Density 0.333%

    No Known Activations