© 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. 60637
    Prev
    Next
    INDEX
    Explanations

    forms of 'to be' or 'is'

    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
     presumably
    -0.17
    å¾Ģå¾Ģæĺ¯
    -0.15
    å¾Ģå¾Ģ
    -0.14
    å¾Īåı¯èĥ½
    -0.14
     typically
    -0.14
    å¾Ģå¾Ģä¼ļ
    -0.14
     often
    -0.13
     usually
    -0.13
     essentially
    -0.13
     apparently
    -0.13
    POSITIVE LOGITS
     alguna
    0.11
     algún
    0.11
    æŁIJç§į
    0.11
    æŁIJ个
    0.10
     algum
    0.10
    å°±å¤ŁäºĨ
    0.10
     saja
    0.10
    ä¹Łåĥı
    0.09
    ä¸įå¤Ł
    0.09
     κάÏĢο
    0.09
    Activations Density 0.090%

    No Known Activations