© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 47765
    Prev
    Next
    INDEX
    Explanations

    specific prepositions indicating relation

    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
    âĸ´
    -0.09
    omorphic
    -0.09
     Revenge
    -0.09
    âĸ·
    -0.09
    íĻĺ
    -0.09
    ï¿Ń
    -0.09
    _exceptions
    -0.09
    érique
    -0.08
    Æ°á»Ľng
    -0.08
    âĸĬ
    -0.08
    POSITIVE LOGITS
    éĤ£ç§į
    0.09
    è¿Ļç§įäºĭæĥħ
    0.09
    åIJĪä½ľåħ³ç³»
    0.09
    æĬķèµĦåŁºéĩij
    0.09
    eland
    0.09
    æĪIJè´¥
    0.08
    举æŃ¢
    0.08
    å°ıå°ıçļĦ
    0.08
    éħįæľī
    0.08
    æľ¬åĽ½
    0.08
    Activations Density 0.418%

    No Known Activations