© 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. 11292
    Prev
    Next
    INDEX
    Explanations

    finite sets and unions

    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
    iliz
    -0.07
    ç»Ĩéķ¿
    -0.07
    Hin
    -0.07
    itre
    -0.07
    veren
    -0.07
     Drit
    -0.07
    attles
    -0.07
    éĩijæĸ¯
    -0.07
    ož
    -0.07
    igny
    -0.07
    POSITIVE LOGITS
    æĪĸå°ij
    0.09
    æĪĸå¤ļ
    0.08
    为ä¹ĭ
    0.07
    为æķ°
    0.07
    èĥĥçĹĽ
    0.07
    imax
    0.07
    ãģĺãĤģ
    0.07
    åĩłäºº
    0.06
    AGMENT
    0.06
    orners
    0.06
    Activations Density 0.007%

    No Known Activations