© 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. 21651
    Prev
    Next
    INDEX
    Explanations

    math expressions

    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
    GLOBALS
    -0.07
    UMB
    -0.07
    å¹³éĺ³
    -0.07
    ecker
    -0.07
    ç§ĴéĴŁ
    -0.07
    çļĦä¸Ģ对
    -0.07
    次åħĥ
    -0.06
    ihi
    -0.06
    picker
    -0.06
    éĻĽ
    -0.06
    POSITIVE LOGITS
    enchmark
    0.08
    patches
    0.07
    enty
    0.07
    benchmark
    0.07
    formatted
    0.07
    æıIJä¾ĽæĽ´å¤ļ
    0.07
    ManagerInterface
    0.06
    oden
    0.06
    -mean
    0.06
    quets
    0.06
    Activations Density 0.003%

    No Known Activations