© 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. 10811
    Prev
    Next
    INDEX
    Explanations

    matter and charge constituents

    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
    åĽ½å¼º
    -0.08
     involving
    -0.08
    achte
    -0.08
    echa
    -0.07
    ikon
    -0.07
    ÛĮکا
    -0.07
    å¤ļä½į
    -0.07
    forme
    -0.07
    iken
    -0.07
     cáp
    -0.07
    POSITIVE LOGITS
    éĹ´çļĦ
    0.11
    éĹ´
    0.10
    å¯Ĩ度
    0.09
    ä¹ĭéĹ´çļĦè·Ŀ离
    0.08
     Density
    0.08
     density
    0.08
    éĸĵçļĦ
    0.08
    åľ¨éĩĮéĿ¢
    0.08
    们
    0.08
    à¸Ĭà¸Ļ
    0.08
    Activations Density 0.005%

    No Known Activations