© 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. 19559
    Prev
    Next
    INDEX
    Explanations

    possessive 's or contractions

    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
    ÑģÑı
    -0.11
    ़
    -0.10
    اÙĭ
    -0.09
    ÏĤ
    -0.09
    аем
    -0.09
    ments
    -0.09
    çļĦå°±æĺ¯
    -0.09
    ä¹ĭ乡
    -0.09
    аÑģÑĮ
    -0.08
    enho
    -0.08
    POSITIVE LOGITS
     dozen
    0.07
    iled
    0.07
    _RESULTS
    0.06
    Ø¢ÙĪر
    0.06
    weeney
    0.06
    ึà¹īà¸ĩ
    0.06
    ovement
    0.06
    apping
    0.06
    جرÙĬ
    0.06
    éĺħè¯»æľ¬æĸĩåīį
    0.06
    Activations Density 0.008%

    No Known Activations