© 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. 14605
    Prev
    Next
    INDEX
    Explanations

    metaphor, allegory, symbol

    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
    ä¸įèµ·
    -0.08
    æķijåij½
    -0.07
    "display
    -0.07
     خصÙĪصÛĮ
    -0.07
    quiries
    -0.07
    _magic
    -0.07
    鬼ç¥ŀ
    -0.07
    RelativeTo
    -0.07
    夯
    -0.07
    ä¸ĵç§ij
    -0.07
    POSITIVE LOGITS
    éļIJåĸ»
    0.13
    åĸ»
    0.13
    象å¾ģ
    0.12
    象å¾ģçĿĢ
    0.10
     symbol
    0.10
    象徵
    0.10
    æ¯Ķåĸ»
    0.10
     metaphor
    0.10
    å¯ĵæĦı
    0.09
     алле
    0.09
    Activations Density 0.065%

    No Known Activations