© 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. 31353
    Prev
    Next
    INDEX
    Explanations

    customs and traditions

    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
    æ³Ľ
    -0.09
    stairs
    -0.08
    饿
    -0.08
    楼梯
    -0.08
     Dream
    -0.08
    æĶ¹éĢł
    -0.08
    æŁ¥
    -0.08
    rô
    -0.08
    è¿Ļåĩł
    -0.08
     Rogers
    -0.08
    POSITIVE LOGITS
    é£İä¿Ĺ
    0.24
    ä¹łä¿Ĺ
    0.24
     customs
    0.18
    æĥ¯ä¾ĭ
    0.14
    ä¹łæĥ¯
    0.14
     Customs
    0.13
    çĶŁæ´»ä¹łæĥ¯
    0.13
    æ°ijä¿Ĺ
    0.13
     practices
    0.12
     traditions
    0.12
    Activations Density 0.077%

    No Known Activations