© 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. 20231
    Prev
    Next
    INDEX
    Explanations

    light traveling through media

    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
    ãģ«ãģĦãĤĭ
    -0.07
     situ
    -0.07
    vend
    -0.06
    NEWS
    -0.06
    ä¸ĬçĶ¨
    -0.06
     abund
    -0.06
    ä¸Ĭæĸ°
    -0.06
    æijĨæĶ¾
    -0.06
     Vend
    -0.06
    ä½įç½®
    -0.06
    POSITIVE LOGITS
    ç©¿è¿ĩ
    0.14
     travers
    0.13
     passing
    0.13
    ç©¿è¶Ĭ
    0.13
    顺åĪ©éĢļè¿ĩ
    0.13
     traverse
    0.13
    éĢĶç»ı
    0.12
     melewati
    0.12
     íĨµê³¼
    0.11
     traveling
    0.11
    Activations Density 0.345%

    No Known Activations