© 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. 45312
    Prev
    Next
    INDEX
    Explanations

    direction and compass headings

    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
    éĩĮäºļ
    -0.07
    æ¡¥åĮº
    -0.06
    ä¸įèı²
    -0.06
    蹦
    -0.06
    oup
    -0.06
    åİļ度
    -0.06
    anden
    -0.06
    erox
    -0.06
     transparent
    -0.06
    æľīæĪIJæķĪ
    -0.06
    POSITIVE LOGITS
    æĸ¹ä½į
    0.12
     Direction
    0.12
    Direction
    0.12
    æĸ¹åIJij
    0.12
     compass
    0.12
     direction
    0.12
    direction
    0.12
    æĸ¹åIJijçļĦ
    0.11
     напÑĢавлений
    0.11
    à¸Ĺิศà¸Ĺาà¸ĩ
    0.11
    Activations Density 0.018%

    No Known Activations