© 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. 57048
    Prev
    Next
    INDEX
    Explanations

    message id key server delivered

    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
    åŁĥå°Ķ
    -0.07
    egu
    -0.07
     ÃĤ
    -0.07
    isert
    -0.07
     Tot
    -0.07
    plr
    -0.06
    fixtures
    -0.06
    è¿
    -0.06
    æĮ
    -0.06
    éĺ¶
    -0.06
    POSITIVE LOGITS
    ä½Ĩçİ°åľ¨
    0.09
     traditionally
    0.09
    èĻ½çĦ¶çİ°åľ¨
    0.08
    gan
    0.08
     whatever
    0.08
    вно
    0.07
    ä½Ĩèĭ¥
    0.07
    (?)
    0.07
     Whatever
    0.07
     historically
    0.07
    Activations Density 0.333%

    No Known Activations