© 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. 33990
    Prev
    Next
    INDEX
    Explanations

    inverse is its transpose

    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
    zman
    -0.07
    éĢŀ
    -0.06
    æĮīæ¯Ķä¾ĭ
    -0.06
    精讲
    -0.06
    æĺ¯ä¸Ģ段
    -0.06
     ÑĦедеÑĢалÑĮного
    -0.06
     Prosper
    -0.06
    ENUM
    -0.06
     Mans
    -0.06
     staged
    -0.06
    POSITIVE LOGITS
     transpose
    0.11
    éķľåĥı
    0.09
    transpose
    0.09
     swapping
    0.09
    mirror
    0.09
    Mirror
    0.09
     mirror
    0.09
     اÙĨع
    0.08
     Mirror
    0.08
     reflection
    0.08
    Activations Density 0.006%

    No Known Activations