© 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. 22239
    Prev
    Next
    INDEX
    Explanations

    numbers followed by particles

    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
    мно
    -0.07
    اÙģع
    -0.07
    elage
    -0.07
    auc
    -0.07
    é¼ĵ
    -0.07
    apur
    -0.07
    orong
    -0.06
    _CID
    -0.06
    Ứ
    -0.06
    Ø¡
    -0.06
    POSITIVE LOGITS
    åIJĥåĪ°
    0.06
    ÏĢάν
    0.06
    irem
    0.06
    æĬĬæīĭ
    0.06
    jis
    0.06
    ersp
    0.06
    CTL
    0.06
     McKay
    0.06
    ocht
    0.06
    STD
    0.06
    Activations Density 0.793%

    No Known Activations