© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16129
    Prev
    Next
    INDEX
    Explanations

    periodic functions or circles

    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
     crus
    -0.08
    æ·ĭæ¼ĵ
    -0.08
    æĿı
    -0.07
    Cascade
    -0.07
    ä¸ŃæĪIJéķ¿
    -0.07
     cascade
    -0.07
    orch
    -0.07
    _EXEC
    -0.07
    USH
    -0.07
    оÑĩи
    -0.07
    POSITIVE LOGITS
    åij¨æľŁæĢ§
    0.10
    åij¨æľŁ
    0.09
     circumference
    0.09
     periodic
    0.09
    .cycle
    0.08
     Rot
    0.08
     cyclic
    0.08
    ÑģÑĤÑı
    0.07
    循çݯ
    0.07
    rot
    0.07
    Activations Density 0.012%

    No Known Activations