© 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. 38824
    Prev
    Next
    INDEX
    Explanations

    orthogonal vectors and spaces

    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
    åįķä½ĵ
    -0.07
    cese
    -0.07
    ç³»åĪĹ
    -0.07
    -indent
    -0.07
    èĻŁç¢¼
    -0.07
    åĪ·å±ı
    -0.07
     Series
    -0.07
    PropertyValue
    -0.07
     ÏĦÏį
    -0.07
    Detailed
    -0.06
    POSITIVE LOGITS
    空éĹ´
    0.10
    空éĸĵ
    0.09
    空éĹ´åĴĮ
    0.09
    -vector
    0.09
     space
    0.08
     orthogonal
    0.08
     vectors
    0.08
    _vectors
    0.08
    Vectors
    0.08
    空éĹ´ä¸Ń
    0.08
    Activations Density 0.008%

    No Known Activations