© 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. 12061
    Prev
    Next
    INDEX
    Explanations

    polar coordinates or plots

    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
    çģĮ
    -0.08
    )[:
    -0.07
    ç³»
    -0.07
    å·¥ä¸ļåĮĸ
    -0.07
     rial
    -0.07
    çªĦ
    -0.06
    ä¸īåı£
    -0.06
    ymar
    -0.06
    allas
    -0.06
     cloned
    -0.06
    POSITIVE LOGITS
    zog
    0.08
    æ¯ıä¸Ģ个åѦçĶŁ
    0.08
     coordinates
    0.08
     Maritime
    0.08
    rawn
    0.07
    ä½įç½®çļĦ
    0.07
     Coordinates
    0.07
     polar
    0.07
    ัà¹Īà¸ĩ
    0.07
    άÏĤ
    0.07
    Activations Density 0.007%

    No Known Activations