© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46645
    Prev
    Next
    INDEX
    Explanations

    friendship and relationships

    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
    _LSB
    -0.08
    ä¸įä½ıäºĨ
    -0.07
    ains
    -0.07
    çĮ®ç»Ļ
    -0.06
    ä¸įåĩºåİ»
    -0.06
     revient
    -0.06
    人人éĥ½
    -0.06
    izi
    -0.06
    azy
    -0.06
    .Annotations
    -0.06
    POSITIVE LOGITS
     mutual
    0.16
    å½¼æѤ
    0.16
    å½¼æѤçļĦ
    0.15
    åıĮæĸ¹çļĦ
    0.14
     mutually
    0.14
     بÙĬÙĨÙĩÙħا
    0.14
     Mutual
    0.13
     взаим
    0.13
    åıĮæĸ¹åľ¨
    0.13
    ãģĬäºĴ
    0.13
    Activations Density 0.263%

    No Known Activations