© 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. 61433
    Prev
    Next
    INDEX
    Explanations

    tangent to bundles and planes

    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
     series
    -0.09
     SERIES
    -0.08
    ç³»åĪĹçļĦ
    -0.08
    ostat
    -0.08
    series
    -0.08
    åĸľæ¬¢ä¸Ĭ
    -0.08
    ARIABLE
    -0.08
    .series
    -0.08
    etin
    -0.07
    strup
    -0.07
    POSITIVE LOGITS
    æĸ¹åIJij
    0.10
     direction
    0.08
     directions
    0.08
     vectors
    0.08
    çļĦæĸ¹åIJij
    0.08
    angent
    0.08
     напÑĢавлениÑı
    0.08
    -vector
    0.07
     tangent
    0.07
    æĸ¹åIJijçļĦ
    0.07
    Activations Density 0.008%

    No Known Activations