© 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. 64101
    Prev
    Next
    INDEX
    Explanations

    punctuation and sentence enders

    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
    æīĢä»¥åľ¨
    -0.08
     severely
    -0.06
    /
    -0.06
    ement
    -0.06
    -0.06
    elin
    -0.06
    el
    -0.06
    emo
    -0.06
    енÑĮ
    -0.06
    表çİ°åľ¨
    -0.06
    POSITIVE LOGITS
    ffy
    0.09
    kis
    0.09
    лове
    0.08
    quoise
    0.08
    OMIC
    0.08
     обÑĬемом
    0.08
    -unstyled
    0.08
    rige
    0.08
    anic
    0.08
    iced
    0.08
    Activations Density 0.005%

    No Known Activations