© 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. 14891
    Prev
    Next
    INDEX
    Explanations

    rotation and 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
    íĻĢ
    -0.07
    æĿĢæīĭ
    -0.07
     lengths
    -0.07
    åijµ
    -0.07
    跨年
    -0.07
    å°ıåŁİ
    -0.07
     Disponibilité
    -0.07
    .GetLength
    -0.07
    &W
    -0.07
    æķ°éĩı
    -0.07
    POSITIVE LOGITS
    à¹Ħà¸Ľà¸ģัà¸ļ
    0.08
    è·Łéļı
    0.08
     velocity
    0.08
    åħ±åIJĮçļĦ
    0.08
    Velocity
    0.07
    velocity
    0.07
     acompan
    0.07
     seamless
    0.07
     Velocity
    0.07
     inert
    0.07
    Activations Density 0.021%

    No Known Activations