© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8850
    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
    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
    iot
    -0.09
    inent
    -0.09
    iche
    -0.09
    åıĬåħ¶
    -0.09
    æµİ
    -0.08
    æīĵåħ¥
    -0.08
    åĩºå·®
    -0.08
    ä¸İä¼Ĺ
    -0.08
    éŀĺ
    -0.08
     aka
    -0.07
    POSITIVE LOGITS
     Depot
    0.10
     Vand
    0.10
    身åŃIJ
    0.09
    女æĸ¹
    0.09
    彩ç¥ŀ
    0.09
    _residual
    0.09
     Stevenson
    0.09
     Dtype
    0.09
    ties
    0.09
    æ¤Ł
    0.09
    Activations Density 0.158%

    No Known Activations