© 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. 49446
    Prev
    Next
    INDEX
    Explanations

    oscillating and cyclical phenomena

    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
    ä¸įæĸ¹ä¾¿
    -0.08
    ivy
    -0.08
    æĸ¹ä¾¿
    -0.07
     tiá»ĩn
    -0.07
    à¸´à¸Ľ
    -0.07
    verband
    -0.07
     Humanities
    -0.07
    åĨ°åĨ°
    -0.07
    èµĦæºIJç½ij
    -0.07
     Omni
    -0.07
    POSITIVE LOGITS
     stable
    0.10
     instability
    0.09
     phenomena
    0.09
    稳å®ļçļĦ
    0.09
     regimes
    0.09
     oscill
    0.09
    stable
    0.09
     unstable
    0.09
     bist
    0.09
     régime
    0.09
    Activations Density 0.152%

    No Known Activations