© 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. 65000
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and operators

    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
    uson
    -0.09
     Vesti
    -0.08
    顶ä¸Ĭ
    -0.08
    ail
    -0.08
    太ä»ĵ
    -0.08
    ipel
    -0.08
    _PI
    -0.08
     Siri
    -0.08
    abox
    -0.08
    è¿Ŀæ³ķåĴĮä¸įèī¯
    -0.07
    POSITIVE LOGITS
    isma
    0.08
    讲课
    0.07
    ä¼łéĢĴ
    0.07
    ä¼łåĩº
    0.07
     outputs
    0.07
    eman
    0.07
    emic
    0.06
    verst
    0.06
    è¿ŀ带
    0.06
    jom
    0.06
    Activations Density 0.002%

    No Known Activations