© 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. 23770
    Prev
    Next
    INDEX
    Explanations

    title and affiliation

    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
    åľ¨å¿ĥä¸Ń
    -0.08
     ourselves
    -0.08
    åľ¨å¿ĥéĩĮ
    -0.08
     yourselves
    -0.07
    ×ķתר
    -0.07
    oners
    -0.07
    orsz
    -0.07
    使å®ĥ
    -0.07
    åĽŀèį¡
    -0.07
    åľ¨è¿Ļ个ä¸ĸçķĮä¸Ĭ
    -0.07
    POSITIVE LOGITS
    åħ·æľī丰å¯ĮçļĦ
    0.08
    æľī丰å¯ĮçļĦ
    0.07
    panion
    0.07
    æŃ¤æ¬¡
    0.07
    æĭ¥æľī丰å¯ĮçļĦ
    0.07
    缮åīįæĺ¯
    0.07
    è´Łè´£å¯¹
    0.07
    çļĦä»ĸ
    0.07
    åħ¼
    0.07
    主åĬ¨åIJij
    0.07
    Activations Density 0.790%

    No Known Activations