© 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. 20630
    Prev
    Next
    INDEX
    Explanations

    produce final product

    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
    åĬ©åѦ
    -0.07
    æł¼
    -0.07
    à¸Ńà¸ĩ
    -0.07
     Bát
    -0.07
    宵
    -0.07
    æij¸æİĴ
    -0.07
    åĴĮ交æµģ
    -0.06
     Bite
    -0.06
     Wend
    -0.06
    agna
    -0.06
    POSITIVE LOGITS
     final
    0.11
    Final
    0.10
     finally
    0.10
    çļĦæľĢç»Ī
    0.10
    æľĢç»Ī
    0.10
    final
    0.09
     Final
    0.09
     ìµľì¢ħ
    0.09
    FINAL
    0.09
    æľĢç»ĪçļĦ
    0.09
    Activations Density 0.013%

    No Known Activations