© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22065
    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
    Not in Any Lists

    No Comments

    Negative Logits
    ÙĪص
    -0.06
    inder
    -0.05
    raj
    -0.05
     Super
    -0.05
    V
    -0.05
    immer
    -0.05
    Super
    -0.05
    .create
    -0.04
     H
    -0.04
     group
    -0.04
    POSITIVE LOGITS
    åľ¨èº«
    0.06
    积åİĭ
    0.06
    å©
    0.06
    ä»Ģä¹ĪæĥħåĨµ
    0.06
    icoli
    0.06
    ëŀŃ
    0.06
    lish
    0.06
    çĴĭ
    0.06
    æ¿¡
    0.06
    lica
    0.06
    Activations Density 0.004%

    No Known Activations