© 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. 13061
    Prev
    Next
    INDEX
    Explanations

    end of C++ code loops

    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
    å¾Īå¤ļäººåľ¨
    -0.08
    kot
    -0.08
    æĺŁäºº
    -0.08
    ulli
    -0.08
    士å®ĺ
    -0.08
     رØŃÙħ
    -0.08
    chado
    -0.07
    spy
    -0.07
    :focus
    -0.07
    chez
    -0.07
    POSITIVE LOGITS
     topic
    0.07
    åıijçİ°
    0.07
    åıijçİ°åĴĮ
    0.06
    idd
    0.06
    oron
    0.06
    ä½łä»¬
    0.06
    uca
    0.06
     resultant
    0.06
     Cour
    0.06
    å¸ĮæľĽä½łä»¬
    0.06
    Activations Density 0.077%

    No Known Activations