© 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. 47077
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming 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
     зла
    -0.07
    trl
    -0.07
    logan
    -0.06
    ulich
    -0.06
    UIS
    -0.06
    æ²³éĩĮ
    -0.06
    +C
    -0.06
    PLE
    -0.06
    åĴĮæľīåħ³
    -0.06
    /mp
    -0.06
    POSITIVE LOGITS
    ç´
    0.07
    ä¸ĢéĹª
    0.07
     (_)
    0.07
    ä½ľçĶ¨äºİ
    0.07
    IfExists
    0.07
    次äºİ
    0.07
    顾åIJįæĢĿä¹ī
    0.07
    ãĥ»
    0.06
    å½ĵå¹´çļĦ
    0.06
    exe
    0.06
    Activations Density 0.051%

    No Known Activations