© 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. 47705
    Prev
    Next
    INDEX
    Explanations

    place names ending in ston or ford

    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
    è¡©
    -0.10
    åľ¨ä»ĸçļĦ
    -0.10
    带æĿ¥çļĦ
    -0.10
    ç»ıéªĮ丰å¯Į
    -0.09
    æīĢ带æĿ¥çļĦ
    -0.09
    å¼ıçļĦ
    -0.09
    Simon
    -0.09
    åľ¨ä»ĸ
    -0.08
    æıIJä¾ĽçļĦ
    -0.08
    åĴĮæĬĢæľ¯
    -0.08
    POSITIVE LOGITS
     Arn
    0.09
    æŃ£å¼ıåIJ¯åĬ¨
    0.09
    zar
    0.09
    ston
    0.09
    UnderTest
    0.09
    彧
    0.09
    ç»ıæµİæĬĢæľ¯
    0.09
    æĭ¼éŁ³
    0.09
    纺
    0.08
    ÙĪÙĨØ©
    0.08
    Activations Density 0.200%

    No Known Activations