© 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. 1405
    Prev
    Next
    INDEX
    Explanations

    boolean logic expressions

    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
    urts
    -0.07
    stw
    -0.07
    abal
    -0.07
    议论
    -0.06
     manti
    -0.06
    çŁ¥ä¹ĭ
    -0.06
    onos
    -0.06
    åı¯èĥ½è¢«
    -0.06
    åĽłä¸ºå®ĥ们
    -0.06
    çļĦæŶåĢĻåı¯ä»¥
    -0.06
    POSITIVE LOGITS
    uke
    0.07
    çĴĢ
    0.07
    åij¼
    0.07
    æĸ¹
    0.07
    çļĩ
    0.07
    andom
    0.07
     decre
    0.07
     SQUARE
    0.06
    亨
    0.06
    æ±Ĥç²¾
    0.06
    Activations Density 0.060%

    No Known Activations