© 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. 48978
    Prev
    Next
    INDEX
    Explanations

    access, time, people, trends

    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
     EÄŁ
    -0.09
     Payne
    -0.09
     Kı
    -0.08
    irse
    -0.08
    mar
    -0.07
    mith
    -0.07
    ãģ¨ãģĦãģ£ãģŁ
    -0.07
     aç
    -0.07
    lug
    -0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.07
    POSITIVE LOGITS
    åĴĮåıijå±ķ
    0.19
    åĴĮæĶ¯æĮģ
    0.17
    建设åĴĮ
    0.16
     and
    0.15
    åĴĮæľįåĬ¡
    0.15
    ç»ıéªĮåĴĮ
    0.14
    管çIJĨåĴĮ
    0.14
    åĴĮæĬĢæľ¯
    0.13
     vÃł
    0.13
    åĴĮå®ĮåĸĦ
    0.13
    Activations Density 1.153%

    No Known Activations