© 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. 31770
    Prev
    Next
    INDEX
    Explanations

    sports teams

    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
    åħ¬å¼Ģåıij
    -0.07
    åģ¿ä»ĺ
    -0.07
    å°ıé¢Ŀ
    -0.06
    amente
    -0.06
    缮çŀª
    -0.06
     Sachs
    -0.06
    ä¸įèĩª
    -0.06
    Å«d
    -0.06
     intim
    -0.06
    anyl
    -0.06
    POSITIVE LOGITS
    ocal
    0.07
    кин
    0.07
    èĨ
    0.07
    éĤĤ
    0.07
    èĤ¥
    0.07
    橱
    0.07
    caf
    0.07
     lazy
    0.07
    è´¨éĩıæ£Ģæµĭ
    0.07
    xx
    0.07
    Activations Density 0.002%

    No Known Activations