© 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. 48551
    Prev
    Next
    INDEX
    Explanations

    jet mills, output iterators, savings accounts, radiation oncology

    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
    å±±ä¹ĭ
    -0.08
    ãģº
    -0.07
    amil
    -0.07
    éħįåIJĪ
    -0.07
    дÑĢе
    -0.07
    æŃ¤äºº
    -0.07
    plevel
    -0.07
    æѤæĸĩ
    -0.07
    atti
    -0.07
    ensible
    -0.06
    POSITIVE LOGITS
     ones
    0.08
    roids
    0.07
    ä¸Ģç±»
    0.07
     systems
    0.07
    ers
    0.06
    å®ĥ们æĺ¯
    0.06
    è®
    0.06
    顾åIJįæĢĿä¹ī
    0.06
    大人们
    0.06
    ç±»
    0.06
    Activations Density 0.036%

    No Known Activations