© 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. 12110
    Prev
    Next
    INDEX
    Explanations

    tables and rankings

    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
     Harvey
    -0.07
    лÑıÑĢ
    -0.07
     décid
    -0.07
    ç»Ŀ
    -0.07
    omi
    -0.07
    çļĦä¸Ģå¥Ĺ
    -0.07
    -dot
    -0.07
     Dot
    -0.07
    çħ§
    -0.07
    amma
    -0.07
    POSITIVE LOGITS
     name
    0.08
    _scheme
    0.08
    åĩ«
    0.07
    [table
    0.07
    å¼Ģå¼ł
    0.07
    alda
    0.06
    å°ı家
    0.06
    <table
    0.06
    acker
    0.06
    table
    0.06
    Activations Density 0.173%

    No Known Activations