© 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. 62693
    Prev
    Next
    INDEX
    Explanations

    web development file extensions

    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
    pont
    -0.07
    åĩ
    -0.07
    —and
    -0.07
    ussion
    -0.07
    –and
    -0.06
    Äħż
    -0.06
     alike
    -0.06
    ulich
    -0.06
    åľĪ
    -0.06
    éŃĦ
    -0.06
    POSITIVE LOGITS
    ä½ķä¸į
    0.08
     samb
    0.07
     maybe
    0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    0.07
    imary
    0.07
    ä¹Łæľī人
    0.07
    inspace
    0.07
    probably
    0.07
     Assoc
    0.07
    ebel
    0.07
    Activations Density 0.002%

    No Known Activations