© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38950
    Prev
    Next
    INDEX
    Explanations

    possessive determiners followed by nouns

    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
    åİ»çľĭ
    -0.09
    éªħ
    -0.09
    æ´¥
    -0.08
    æĹĹ
    -0.08
    agua
    -0.08
    uzzi
    -0.08
    鼨
    -0.08
     duties
    -0.08
    acy
    -0.08
    idas
    -0.08
    POSITIVE LOGITS
    è·
    0.12
    ween
    0.11
    SourceType
    0.09
    æµ·æĭĶ
    0.09
    好è¯Ħ
    0.09
    åŀĨ
    0.09
    容éĩı
    0.09
    æĹłå£°
    0.09
    ç¼Ģ
    0.08
    à¸Ħà¸Ń
    0.08
    Activations Density 0.020%

    No Known Activations