© 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. 10089
    Prev
    Next
    INDEX
    Explanations

    of others

    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
    æĸĩç«łäºĨ
    -0.07
    çļĦæĥħ
    -0.06
    çľĭåľ¨
    -0.06
    åħ¸
    -0.06
    йн
    -0.06
    çļĦé¡¹çĽ®
    -0.06
    mero
    -0.06
    cium
    -0.06
    å¾Ĵ
    -0.06
    åºĨç¥Ŀä¸ŃåĽ½åħ±äº§åħļæĪIJç«ĭ
    -0.06
    POSITIVE LOGITS
     these
    0.15
     thereof
    0.15
    è¿ĻäºĽ
    0.15
     daarvan
    0.14
     ÑįÑĤиÑħ
    0.13
     hierv
    0.13
     this
    0.13
     davon
    0.13
    éĢĻäºĽ
    0.13
     ervan
    0.13
    Activations Density 1.005%

    No Known Activations