© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 11159
    Prev
    Next
    INDEX
    Explanations

    multi-electrical device design

    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
    .Dial
    -0.08
    engers
    -0.08
    ego
    -0.07
    \/\/
    -0.07
    è´Ŀ
    -0.07
    endid
    -0.07
    巴马
    -0.07
    ç¾İå¦Ļ
    -0.07
    udid
    -0.07
    [Math
    -0.07
    POSITIVE LOGITS
    ogat
    0.08
    çĴĭ
    0.07
    heu
    0.07
    åIJĪ
    0.06
    åĪ°èĢģ
    0.06
    æ¦Ľ
    0.06
    cha
    0.06
    eler
    0.06
    é»ijæĿ¿
    0.06
    jÃŃ
    0.06
    Activations Density 0.022%

    No Known Activations