© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7316
    Prev
    Next
    INDEX
    Explanations

    possessive 's or related possessives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    æķĸ
    -0.09
     Hastings
    -0.08
    空æ°Ķä¸Ń
    -0.08
    æķ´ä¸ªäºº
    -0.08
    é£İåIJ¹
    -0.08
    acula
    -0.08
    æīĢèĥ½
    -0.08
    èĥ¥
    -0.08
    orz
    -0.07
    å¤ı
    -0.07
    POSITIVE LOGITS
    åĪ«äººçļĦ
    0.23
    ä»ĸ人
    0.16
    åĪ«äºº
    0.16
    ç»ĻåĪ«äºº
    0.12
    åĪ¥äºº
    0.11
    åĪ«çļĦ
    0.10
    åĢŁçĶ¨
    0.10
    æīĢæľīæĿĥ
    0.10
    人家
    0.10
    产æĿĥ
    0.10
    Activations Density 0.094%

    No Known Activations