© 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. 57812
    Prev
    Next
    INDEX
    Explanations

    planets and celestial bodies

    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
    éľĨ
    -0.08
    iette
    -0.07
    SetValue
    -0.07
    ä¼į
    -0.07
    ÙģتÙĩ
    -0.07
    arrow
    -0.07
    _PHY
    -0.07
    æĪ³
    -0.07
    ä¸ĩåıĺ
    -0.06
    شد
    -0.06
    POSITIVE LOGITS
    离æĪij们
    0.08
     nearer
    0.08
    èµĦæºIJ丰å¯Į
    0.07
     газо
    0.07
    uzzi
    0.07
    еÑģе
    0.07
    åĸĢ
    0.07
     Venus
    0.07
    UNCH
    0.07
     manned
    0.07
    Activations Density 0.011%

    No Known Activations