© 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. 12948
    Prev
    Next
    INDEX
    Explanations

    possessive apostrophes

    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
    .zone
    -0.08
    atee
    -0.07
    erson
    -0.07
    ;</
    -0.07
    iento
    -0.07
    ÛĮشاÙĨ
    -0.07
    otton
    -0.07
    ply
    -0.07
    год
    -0.07
    anyon
    -0.07
    POSITIVE LOGITS
     iepazÄ«Å¡anÄģs
    0.07
    елÑĮ
    0.06
    elsing
    0.06
    uppen
    0.06
    æĮªçĶ¨
    0.06
    ä¸įéĢļ
    0.06
    åİ¿å§Ķ书记
    0.06
    élection
    0.06
     нама
    0.06
    ijker
    0.06
    Activations Density 0.016%

    No Known Activations