© 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. 25011
    Prev
    Next
    INDEX
    Explanations

    astronomical orbit and rotation concepts

    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
    upas
    -0.07
    éĴ»åŃĶ
    -0.07
    åı¯ä¹IJ
    -0.07
    ä¸ĸ纪åĪĿ
    -0.06
    alische
    -0.06
    路人
    -0.06
    usan
    -0.06
    либо
    -0.06
    æĮł
    -0.06
    ลัà¸ĩ
    -0.06
    POSITIVE LOGITS
     yearly
    0.08
    ä½ľæĽ²
    0.08
    åŃ£
    0.08
     ì¶Ķ
    0.07
     erk
    0.07
    Resizable
    0.07
    è¹´
    0.07
     brac
    0.07
     seasonal
    0.07
    é¢
    0.07
    Activations Density 0.006%

    No Known Activations