© 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. 36089
    Prev
    Next
    INDEX
    Explanations

    years, anniversaries, or numerical periods

    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
    稳妥
    -0.09
    幡
    -0.09
    оÑĩка
    -0.09
    etal
    -0.09
    éļ°
    -0.08
    ä¹ĭåĬ¿
    -0.08
    åĩºåľº
    -0.08
    (layers
    -0.08
    èĢĥè¯ģ
    -0.08
    ãĥĹãĥª
    -0.08
    POSITIVE LOGITS
    YLE
    0.09
    åļ
    0.08
    责任ç¼ĸè¾ij
    0.08
    athed
    0.08
    ÑİÑĢ
    0.08
    æĶ¹éĿ©å¼ĢæĶ¾
    0.08
    oleon
    0.08
    èĨº
    0.08
    ynthesis
    0.07
    paged
    0.07
    Activations Density 0.045%

    No Known Activations