© 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. 951
    Prev
    Next
    INDEX
    Explanations

    thinking about

    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
    acman
    -0.08
     reportedly
    -0.08
    详解
    -0.07
    laš
    -0.07
    æĪĸå°Ĩ
    -0.07
    .getMethod
    -0.07
    entrum
    -0.07
    criptor
    -0.07
    ottom
    -0.07
     lu
    -0.07
    POSITIVE LOGITS
    ãĤĤãģĹ
    0.08
     whether
    0.08
    å¦ĤæŀľæĬĬ
    0.08
    æĺ¯åIJ¦åı¯ä»¥
    0.08
    ä¼ļä¸įä¼ļ
    0.08
    æĺ¯åIJ¦åŃĺåľ¨
    0.08
    ä¸Ģæĥ³
    0.08
     possibilities
    0.08
    æĺ¯åIJ¦éľĢè¦ģ
    0.08
     how
    0.08
    Activations Density 0.021%

    No Known Activations