© 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. 37991
    Prev
    Next
    INDEX
    Explanations

    growing demands

    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
    åı¯æł¹æį®
    -0.11
    ums
    -0.10
    eneg
    -0.10
     ÑĥдалоÑģÑĮ
    -0.09
    饱
    -0.09
    æĿĥå¨ģ
    -0.09
    ä¹ĭåĨħ
    -0.09
     çev
    -0.09
    enk
    -0.09
    大æĪĺ
    -0.09
    POSITIVE LOGITS
    æĹ¥çĽĬ
    0.12
    åºŀ大çļĦ
    0.11
    åºŀ大
    0.11
    ä¸ĩä¸Ģ
    0.11
    带æĿ¥çļĦ
    0.11
    æīĢéľĢçļĦ
    0.11
    æĸ°å½¢åĬ¿
    0.10
     demands
    0.10
    éĤ£ä¹Īå¤ļ
    0.10
    è¿Ļä¹Īå¤ļ
    0.10
    Activations Density 0.275%

    No Known Activations