© 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. 30803
    Prev
    Next
    INDEX
    Explanations

    orthogonal vectors

    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
    åģľé¡¿
    -0.08
    åģľåľ¨
    -0.07
    æ¯ı件
    -0.07
    .nasa
    -0.07
    èĢ½è¯¯
    -0.07
     паÑĥ
    -0.07
    æľĽ
    -0.07
    éģĩä¸Ĭ
    -0.07
    èĴ¸
    -0.07
    延误
    -0.07
    POSITIVE LOGITS
     orthogonal
    0.13
     Orth
    0.10
     vectors
    0.09
    åŀĤ缴
    0.09
    Vectors
    0.09
    Orth
    0.09
     perpendicular
    0.09
    åIJijéĩı
    0.08
     orth
    0.08
    vecs
    0.08
    Activations Density 0.006%

    No Known Activations