© 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. 60991
    Prev
    Next
    INDEX
    Explanations

    scientific discoveries and researchers

    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
    æijĬ
    -0.07
     prescriptions
    -0.07
    keh
    -0.07
    _funcs
    -0.07
    èµĦ
    -0.07
    frig
    -0.07
     berkom
    -0.07
    åĨ»ç»ĵ
    -0.07
    éĨīäºĨ
    -0.07
    æĭĽæīĭ
    -0.06
    POSITIVE LOGITS
     experiment
    0.13
    å®ŀéªĮä¸Ń
    0.11
    experiment
    0.11
    å®ŀéªĮ
    0.11
     Experiment
    0.10
     experiments
    0.10
    實é©Ĺ
    0.10
    Experiment
    0.09
    periment
    0.09
     ÑįкÑģпеÑĢим
    0.09
    Activations Density 0.014%

    No Known Activations