© 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. 58729
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by nouns

    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
    _PTR
    -0.07
    eka
    -0.07
    anke
    -0.07
    armo
    -0.07
    ÑĦиÑĢ
    -0.07
    abr
    -0.07
    itably
    -0.07
    .Types
    -0.07
    åħĪéĶĭ模èĮĥ
    -0.06
    ми
    -0.06
    POSITIVE LOGITS
    çĴ¨
    0.09
    èĩªå·±
    0.08
    ilet
    0.07
    ç«Ļç«Ļ
    0.07
     spos
    0.07
    ly
    0.07
     own
    0.07
    èĩªå·±èº«ä¸Ĭ
    0.07
    ited
    0.06
    èĨł
    0.06
    Activations Density 0.007%

    No Known Activations