© 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. 51048
    Prev
    Next
    INDEX
    Explanations

    former, formerly, previously

    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
    åĦ¿å¥³
    -0.07
    è¿Ļç§įä¸ľè¥¿
    -0.07
    ä¼ļæľīä¸Ģ个
    -0.07
    人æīĭ
    -0.07
    åı«
    -0.07
    人æķĻçīĪ
    -0.07
    è¿Ļåı«
    -0.07
    ä½ļåIJį
    -0.06
    اÙģÙĦ
    -0.06
    æĪijåı«
    -0.06
    POSITIVE LOGITS
     former
    0.10
     formerly
    0.09
     previously
    0.09
     founding
    0.08
    æĺ¯ä¸ĢåIJį
    0.08
    formerly
    0.08
     aka
    0.08
    æĹ¢æĺ¯
    0.08
     ÑĢанее
    0.08
     titular
    0.07
    Activations Density 0.903%

    No Known Activations