© 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. 4460
    Prev
    Next
    INDEX
    Explanations

    spin ordering, magnetic patterns

    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
    andos
    -0.08
    tables
    -0.07
    æµij
    -0.06
    ä¹ĭæĢ¥
    -0.06
    人ä¸ĸ
    -0.06
     purpos
    -0.06
     scoped
    -0.06
    åij¼
    -0.06
    éĩį大éģĹæ¼ı
    -0.06
    æĿ¥æºIJ
    -0.06
    POSITIVE LOGITS
    åĩĿå¿ĥ
    0.08
    纺
    0.08
    Resolved
    0.08
    è¿IJåĬ¨ä¼ļ
    0.08
    åĽ¾æ¡Ī
    0.08
     spatial
    0.08
     patterns
    0.08
    Pattern
    0.08
     underlying
    0.07
     pattern
    0.07
    Activations Density 0.049%

    No Known Activations