© 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. 10476
    Prev
    Next
    INDEX
    Explanations

    level description

    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¸įå¹²
    -0.07
    è¿Ŀåıįä¸Ĭè¿°
    -0.07
    åĿļæĮģæĬĬ
    -0.07
    ocomplete
    -0.07
    éĩijåŃĹ
    -0.06
    ufer
    -0.06
    ÏĥÏį
    -0.06
    .serialize
    -0.06
    -platform
    -0.06
    èĮģ
    -0.06
    POSITIVE LOGITS
    onta
    0.07
    æĪij常常
    0.07
    -dominated
    0.07
    Ed
    0.07
    .isVisible
    0.07
    ermo
    0.07
    otec
    0.07
    ardin
    0.07
    èĢĮæĿ¥çļĦ
    0.07
    iak
    0.07
    Activations Density 0.006%

    No Known Activations