© 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. 12884
    Prev
    Next
    INDEX
    Explanations

    numbers and roman numerals

    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
    upe
    -0.09
    ArrayType
    -0.09
    bane
    -0.09
    è¿Ŀæ³ķåĴĮä¸įèī¯
    -0.08
    èī²åĪĹ
    -0.08
    zut
    -0.08
    éĻ£
    -0.08
    éĺµ
    -0.08
    é¢IJ
    -0.08
    WEBPACK
    -0.07
    POSITIVE LOGITS
    æīĢ说çļĦ
    0.07
    inch
    0.07
    说çļĦæĺ¯
    0.07
     literally
    0.06
    讲çļĦæĺ¯
    0.06
    _OVERRIDE
    0.06
    æīĢè¨Ģ
    0.06
    èĢģ乡
    0.06
    æıIJåĪ°çļĦ
    0.06
    æīĢ说
    0.06
    Activations Density 0.016%

    No Known Activations