© 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. 9549
    Prev
    Next
    INDEX
    Explanations

    variable depth and wave motion

    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
    ç²¹
    -0.07
    éŁ³è§Ĩé¢ij
    -0.07
    ç©İ
    -0.07
    å±±å·Ŀ
    -0.07
    罡
    -0.07
    äºĮä¸ī
    -0.07
    ä¸į移
    -0.06
    streams
    -0.06
    æĪĸå°ij
    -0.06
    sert
    -0.06
    POSITIVE LOGITS
    éļı
    0.08
    éļıæŶ
    0.08
    åıĺåĮĸçļĦ
    0.08
    éļıçĿĢ
    0.08
    ä¸įæĸŃåıĺåĮĸ
    0.07
    plot
    0.07
    åıĺåĮĸ
    0.07
    次第
    0.07
     variable
    0.07
     decreasing
    0.07
    Activations Density 0.007%

    No Known Activations