© 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. 31453
    Prev
    Next
    INDEX
    Explanations

    names of people and places

    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
    cestor
    -0.07
    å·
    -0.07
    é¤
    -0.07
    arli
    -0.07
    æĩ
    -0.07
    ots
    -0.07
    æ¯Ĺ
    -0.07
    aviest
    -0.07
    мини
    -0.07
    artista
    -0.07
    POSITIVE LOGITS
    æ¯ķç«Łæĺ¯
    0.08
    æĽ´åĥı
    0.07
    ignan
    0.07
    ejo
    0.07
    æĪĺ线
    0.07
     arguably
    0.07
    容æĺĵå¼ķèµ·
    0.07
    पाल
    0.07
    æĽ´åĥıæĺ¯
    0.07
    åģļåĪ°çļĦ
    0.06
    Activations Density 0.012%

    No Known Activations