© 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. 10129
    Prev
    Next
    INDEX
    Explanations

    either or like

    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
    naan
    -0.07
     Constru
    -0.07
    è¿Ļ便æĺ¯
    -0.07
    转载请注æĺİ
    -0.07
    illé
    -0.07
    æĥ³å¾Ĺ
    -0.07
    nown
    -0.07
    airy
    -0.07
     ÐłÑı
    -0.06
    grab
    -0.06
    POSITIVE LOGITS
     presumably
    0.11
    æĮĩçļĦæĺ¯
    0.10
    umably
    0.10
    æĦıåij³çĿĢ
    0.10
     Means
    0.09
    æĮĩ
    0.09
     means
    0.09
    ãģ¤ãģ¾ãĤĬ
    0.08
    ä¹Łå°±æĺ¯
    0.08
    æĺ¯æĮĩ
    0.08
    Activations Density 0.112%

    No Known Activations