© 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. 22987
    Prev
    Next
    INDEX
    Explanations

    coordinates and geometry calculations

    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
    ä¼´æľī
    -0.07
    丼æŀĹ
    -0.07
    avera
    -0.06
    æŀĹä¸Ń
    -0.06
    able
    -0.06
    åIJŀåIJIJ
    -0.06
    å¹´åįİ
    -0.06
    æŁ¥
    -0.06
    Ñĩем
    -0.06
     pelle
    -0.06
    POSITIVE LOGITS
     coordinates
    0.12
    coordinates
    0.12
    åĿIJæłĩ
    0.11
     Coordinates
    0.10
    Coordinates
    0.10
    åĿIJæłĩç³»
    0.10
    _representation
    0.09
     coordinate
    0.09
     representation
    0.09
    -coordinate
    0.09
    Activations Density 0.009%

    No Known Activations