© 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. 44029
    Prev
    Next
    INDEX
    Explanations

    list item identifiers

    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
    isses
    -0.07
    æĹ¢æľī
    -0.07
    thumb
    -0.07
    åĽ¾åĨĮ
    -0.07
    å¤ļåĬ¨
    -0.06
    ]?.
    -0.06
    çĻ¾äº¿
    -0.06
     عÙĨÙĩ
    -0.06
    åıĤèĢĥèµĦæĸĻ
    -0.06
    elop
    -0.06
    POSITIVE LOGITS
    æł·åŃIJ
    0.07
    æĴĩ
    0.07
    åĢ¼
    0.07
    æ¨¡æł·
    0.07
    éľľ
    0.07
    è¿Ķ
    0.07
    åIJ¬å¾Ĺ
    0.07
    対
    0.07
    /renderer
    0.06
    йма
    0.06
    Activations Density 0.111%

    No Known Activations