© 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. 12224
    Prev
    Next
    INDEX
    Explanations

    Spanish and Hispanic cultures

    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
     Sipil
    -0.07
     Ristorante
    -0.07
    aiser
    -0.07
    éĺ¿å§Ĩæĸ¯çī¹
    -0.07
    亩
    -0.07
    Unhandled
    -0.06
    ä¸ŃåĽ½äººæ°ij解æĶ¾åĨĽ
    -0.06
    inkel
    -0.06
    enu
    -0.06
    象山
    -0.06
    POSITIVE LOGITS
     Spanish
    0.10
    Spanish
    0.10
    马德éĩĮ
    0.10
    Spain
    0.09
    西çıŃçīĻ
    0.09
    æ±¾
    0.09
    æĿıèĬ±
    0.09
    西çıŃçīĻè¯Ń
    0.09
    Ñģпан
    0.09
    åIJķæ¢ģ
    0.08
    Activations Density 0.540%

    No Known Activations