© 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. 56731
    Prev
    Next
    INDEX
    Explanations

    new and recent year of

    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
    æľīç½ijåıĭ
    -0.10
    ä¹°ä¸ľè¥¿
    -0.10
    æĪIJ为ä¸ŃåĽ½
    -0.10
    ä¸ĩæĪ·
    -0.09
    æĢ»èµĦ产
    -0.09
    WithEmail
    -0.09
    æĦĶ
    -0.09
    _versions
    -0.09
    ä¸Ģç«Ļ
    -0.09
    ç³»åĪĹæ´»åĬ¨
    -0.09
    POSITIVE LOGITS
    åĢ¼å¾Ĺåħ³æ³¨
    0.10
     incoming
    0.10
    è¿Ļä¸Ģå¹´
    0.09
    åįģä½³
    0.09
     Incoming
    0.09
    ä»Ĭå¹´
    0.09
    Reviewed
    0.09
    年度
    0.09
    eller
    0.09
    ellers
    0.09
    Activations Density 0.142%

    No Known Activations