© 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. 14685
    Prev
    Next
    INDEX
    Explanations

    Ecma International, Microsoft, java.io

    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
    ä¸ĢæĻĤ
    -0.07
    azzur
    -0.07
    mane
    -0.07
     Speedway
    -0.07
    imore
    -0.07
     redd
    -0.07
    ettino
    -0.07
    ãm
    -0.07
    jim
    -0.07
    æĸĩæѦ
    -0.07
    POSITIVE LOGITS
    éĹĬ
    0.08
    usher
    0.07
    èĢĥçĤ¹
    0.07
    æĴĩ
    0.06
     Rum
    0.06
    дове
    0.06
    дова
    0.06
    æĽ
    0.06
    丰å¯Į
    0.06
    便å°Ĩ
    0.06
    Activations Density 0.001%

    No Known Activations