© 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. 45535
    Prev
    Next
    INDEX
    Explanations

    duplicate questions

    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
    åŃĺåľ¨äºİ
    -0.08
    odon
    -0.07
    éĢļ常æĺ¯
    -0.07
    该项
    -0.07
     anytime
    -0.07
    olan
    -0.07
    çĦ¶å¤§
    -0.07
    æ¯Ķè¾ĥ容æĺĵ
    -0.07
    çĦ¶
    -0.07
    heb
    -0.07
    POSITIVE LOGITS
    ridge
    0.06
    rp
    0.06
     thừa
    0.06
    _super
    0.06
     reconsider
    0.06
    ï¾Ł
    0.06
    交çļĦ
    0.06
    vester
    0.06
    %%%%
    0.06
    WindowSize
    0.06
    Activations Density 0.004%

    No Known Activations