© 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. 53299
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and family

    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
    æĭĩæĮĩ
    -0.11
    æµģæ°ĵ
    -0.10
    è¿Ļ家ä¼Ļ
    -0.09
     Fasc
    -0.09
    缶
    -0.08
    çļĦåĪ°æĿ¥
    -0.08
    _NB
    -0.08
    åľ¨æѤ
    -0.08
    éļıæŶéļı
    -0.08
     Nail
    -0.08
    POSITIVE LOGITS
    å®īå®ģ
    0.09
    Ale
    0.09
     Alo
    0.09
     Continent
    0.09
    documento
    0.09
    åĸĦèī¯
    0.08
    æ°´æºIJ
    0.08
    åºľ
    0.08
     unwanted
    0.08
    mart
    0.08
    Activations Density 0.111%

    No Known Activations