© 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. 24036
    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
    elay
    -0.08
    夫妻
    -0.08
    enstr
    -0.08
    estet
    -0.07
    CADE
    -0.07
    apul
    -0.07
    çĶ¨ä½ľ
    -0.07
    umer
    -0.07
    eur
    -0.06
    ÏĢαν
    -0.06
    POSITIVE LOGITS
     own
    0.18
     Own
    0.12
     OWN
    0.12
    own
    0.10
     respective
    0.10
     sendiri
    0.10
     usual
    0.10
     propres
    0.10
    _own
    0.10
    Own
    0.10
    Activations Density 0.453%

    No Known Activations