© 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. 14767
    Prev
    Next
    INDEX
    Explanations

    code delimiters or math notation

    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
    ην
    -0.07
    mb
    -0.07
    arka
    -0.06
    建设工ç¨ĭæľīéĻIJåħ¬åı¸
    -0.06
    ára
    -0.06
    Files
    -0.06
    afa
    -0.06
    umm
    -0.06
    æľīåģ¿
    -0.06
    abet
    -0.06
    POSITIVE LOGITS
    zyw
    0.09
    -animate
    0.08
    witz
    0.07
    eson
    0.07
    asseur
    0.07
    æ¯ĶæĪij们
    0.07
    egral
    0.07
    èĢĮæĪij们
    0.07
    Ahead
    0.07
    ustes
    0.07
    Activations Density 0.006%

    No Known Activations