© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22509
    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
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    åı¦
    -0.06
    ).-
    -0.05
    anza
    -0.05
    æİ¥
    -0.05
     Photograph
    -0.05
    zis
    -0.05
    åĴĮæľ¬
    -0.05
    apid
    -0.05
     pace
    -0.05
    ilet
    -0.05
    POSITIVE LOGITS
    tier
    0.06
    udin
    0.06
    typeid
    0.06
    åı²çļĦ
    0.06
    ÛĮات
    0.06
     bú
    0.06
    ucher
    0.06
    hani
    0.06
    åĬ¨åĬ¨
    0.06
    ringen
    0.05
    Activations Density 0.001%

    No Known Activations