© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11867
    Prev
    Next
    INDEX
    Explanations

    equation, coefficients, and algebra

    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
     ARCH
    -0.07
     "&#
    -0.07
    èħ³
    -0.07
    à¹Īà¸Ńย
    -0.07
    US
    -0.07
    楼ä¸Ĭ
    -0.06
    uitive
    -0.06
     Sousa
    -0.06
    ÑģÑĤÑĢе
    -0.06
    åIJ¯äºĭ
    -0.06
    POSITIVE LOGITS
    зÑĭ
    0.08
    iever
    0.08
    åĢ©
    0.08
    ساÙĦ
    0.08
     Caz
    0.07
     coordinates
    0.07
    åįĵ
    0.07
     اÙħت
    0.07
     xmlns
    0.07
     Spatial
    0.07
    Activations Density 0.003%

    No Known Activations