© 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. 10717
    Prev
    Next
    INDEX
    Explanations

    offseason and season

    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
    æĬµæĮ¡
    -0.11
    éļıæŶéļı
    -0.10
    urses
    -0.10
    æĬµæĬĹ
    -0.10
    é¢Ĩ
    -0.09
    blas
    -0.09
    ä¸ĭ鼨
    -0.09
    ç©¿
    -0.09
    .Interop
    -0.09
    æĶ¯æı´
    -0.09
    POSITIVE LOGITS
    æĺİå¹´
    0.14
    è¿Ļä¸Ģå¹´
    0.13
     offseason
    0.13
    æĸ°çļĦä¸Ģå¹´
    0.13
    ä¸Ĭå¹´
    0.12
    åݻ年
    0.12
    æıIJåīį
    0.11
    å¹´åĪĿ
    0.10
    æĸ°å¹´
    0.10
     retained
    0.10
    Activations Density 0.111%

    No Known Activations