© 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. 41986
    Prev
    Next
    INDEX
    Explanations

    possessive 's followed by common words

    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
    ়
    -0.10
    gnore
    -0.09
    à§įà¦Ł
    -0.08
    оле
    -0.08
    à¥įà¤ŀ
    -0.08
    à§įদ
    -0.08
    wai
    -0.08
    icals
    -0.08
    strup
    -0.08
    à®ķà¯įà®ķ
    -0.08
    POSITIVE LOGITS
    й
    0.09
    ãĥ¼
    0.09
    britannien
    0.08
     gotta
    0.08
    ய
    0.08
     gonna
    0.08
    ihi
    0.07
    sa
    0.07
     behalf
    0.07
     been
    0.07
    Activations Density 0.405%

    No Known Activations