© 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. 47558
    Prev
    Next
    INDEX
    Explanations

    coupling interactions

    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
    .failure
    -0.07
    åĢ¼å¾Ĺåħ³æ³¨
    -0.06
     status
    -0.06
    åĪĽå®¢
    -0.06
    æ·ĺ
    -0.06
    estatus
    -0.06
    æŦ
    -0.06
    å®ķ
    -0.06
     looming
    -0.06
    æ°´æ´Ĺ
    -0.06
    POSITIVE LOGITS
    ×IJ×Ķ
    0.09
    åľ°ä¹ħ
    0.08
    mlin
    0.08
    sert
    0.08
    交éĢļèŃ¦å¯Ł
    0.08
    ddb
    0.08
    äºĭ件ä¸Ń
    0.08
     linking
    0.07
    outu
    0.07
    mega
    0.07
    Activations Density 0.003%

    No Known Activations