© 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. 8956
    Prev
    Next
    INDEX
    Explanations

    roughly

    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
    ifice
    -0.09
    каде
    -0.09
    æķĻäºİ
    -0.09
    tır
    -0.08
    urga
    -0.08
    ioneer
    -0.08
    رÙĪÙĨ
    -0.08
    tól
    -0.08
    odelist
    -0.08
    ergi
    -0.08
    POSITIVE LOGITS
    ly
    0.12
    ä½Ĩä¸įéĻIJäºİ
    0.11
    er
    0.10
    itarian
    0.09
    ÅŁt
    0.09
    ily
    0.09
    но
    0.09
    -minded
    0.08
    mente
    0.08
    ERENCE
    0.08
    Activations Density 0.023%

    No Known Activations