© 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. 19295
    Prev
    Next
    INDEX
    Explanations

    symmetric arrangement of points

    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
    æ¶ĪåĮĸä¸įèī¯
    -0.07
    Scope
    -0.07
    duck
    -0.07
    Scoped
    -0.07
    Ranges
    -0.07
    PerPixel
    -0.06
    ä¸įèı²
    -0.06
    .Function
    -0.06
    åĸĦæĦı
    -0.06
     scope
    -0.06
    POSITIVE LOGITS
    å½¼æѤ
    0.10
    对称
    0.09
     symmetry
    0.09
    缸éļĶ
    0.09
     symmetric
    0.09
     angles
    0.09
     positions
    0.09
     evenly
    0.09
     distances
    0.08
     arrangement
    0.08
    Activations Density 0.024%

    No Known Activations