© 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. 64316
    Prev
    Next
    INDEX
    Explanations

    growing up, raised, upbringing

    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
     tempting
    -0.08
    ä¸Ĭ次
    -0.08
    é«ĺæł¡çĶŁ
    -0.08
    esterday
    -0.07
    Sexy
    -0.07
    æ´»åĬ¨æŶ
    -0.07
    å©ļæ´»
    -0.07
     lately
    -0.07
    åij¨å¹´çºªå¿µ
    -0.07
    ä¸İåѦçĶŁ
    -0.07
    POSITIVE LOGITS
     upbringing
    0.14
    çĨıéĻ¶
    0.12
    èĩªå¹¼
    0.11
    æĹ©çĨŁ
    0.10
    ä»İå°ıå°±
    0.10
    ä»İå°ı
    0.10
    æ½ľç§»é»ĺ
    0.10
    çģĮè¾ĵ
    0.10
     childhood
    0.09
    æijĩ篮
    0.09
    Activations Density 0.352%

    No Known Activations