© 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. 6989
    Prev
    Next
    INDEX
    Explanations

    crowd and crowds

    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
    èĬ±å¼Ģ
    -0.10
    è¿ľæĸ¹
    -0.09
    å¼ĢèĬ±
    -0.09
    åı¯æĢľ
    -0.08
    æ¨
    -0.08
    unei
    -0.08
    ç¾İå¾·
    -0.08
    è¯ģåĪ¸æĬķèµĦ
    -0.08
    åĪĨæł¡
    -0.08
    çĻ¯
    -0.08
    POSITIVE LOGITS
    æĭ¥æĮ¤
    0.19
    人群
    0.16
    人æµģ
    0.14
    æİĴéĺŁ
    0.14
     crowd
    0.13
    人群ä¸Ń
    0.13
    æĮ¤
    0.12
     crowds
    0.12
    æĭ¥åłµ
    0.12
    crow
    0.12
    Activations Density 0.057%

    No Known Activations