© 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. 51726
    Prev
    Next
    INDEX
    Explanations

    async Task

    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
    aches
    -0.07
    RESET
    -0.07
    izarre
    -0.07
    çıŃéĽĨä½ĵ
    -0.07
    mostat
    -0.07
    istik
    -0.07
    严å®ŀ
    -0.07
    lobals
    -0.07
    æĽ¿ãģĪ
    -0.07
    доÑĢ
    -0.07
    POSITIVE LOGITS
    sor
    0.08
    -await
    0.08
    (async
    0.07
    lime
    0.07
    .Delay
    0.07
    út
    0.07
    sel
    0.07
    mooth
    0.07
    /thread
    0.07
     Ngo
    0.07
    Activations Density 0.053%

    No Known Activations