© 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. 52462
    Prev
    Next
    INDEX
    Explanations

    future or time intervals

    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
    ä¸įåĨį
    -0.10
    åİ»åĵªåĦ¿
    -0.09
    ä¸Ģç»ı
    -0.09
    ç»ıåķĨ
    -0.09
    èĮĥåĽ´åĨħ
    -0.08
    åIJĬ
    -0.08
    顺çĿĢ
    -0.08
    ож
    -0.08
     RANGE
    -0.08
    ãģ©ãģĨãģĦãģĨ
    -0.08
    POSITIVE LOGITS
    å¥
    0.10
    urret
    0.09
    å¾Īéķ¿æŶéĹ´
    0.09
    ç¥ļ
    0.09
    漫éķ¿
    0.09
    MLS
    0.09
    两级
    0.09
    æѤç§į
    0.09
    漫éķ¿çļĦ
    0.08
    /tool
    0.08
    Activations Density 0.175%

    No Known Activations