© 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. 60365
    Prev
    Next
    INDEX
    Explanations

    words like supposedly or correctly

    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
    ihan
    -0.09
    DOMNode
    -0.08
    æľī以ä¸ĭ
    -0.08
    .orig
    -0.07
    è¾Ľåĭ¤çļĦ
    -0.07
     eventdata
    -0.07
    engan
    -0.07
    zap
    -0.07
    çĶ¨å®ĥ
    -0.07
    åIJ¯è¿ª
    -0.07
    POSITIVE LOGITS
     presumably
    0.08
     ÑıкобÑĭ
    0.08
    åį´ä¸įçŁ¥éģĵ
    0.08
    ä½Ĩæĺ¯åį´
    0.07
     supposedly
    0.07
    æŁIJç§į
    0.07
     correctly
    0.07
    èĢĮä¸Ķè¿ĺæĺ¯
    0.07
    çļĦä¸Ģç§į
    0.07
    åı¦ä¸Ģç§į
    0.07
    Activations Density 0.004%

    No Known Activations