© 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. 26903
    Prev
    Next
    INDEX
    Explanations

    swimming

    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
    çIJ¢
    -0.10
    梼
    -0.09
    åĺ´è§Ĵ
    -0.09
    ellation
    -0.09
    à¸Ķาว
    -0.09
    èµ°å»Ĭ
    -0.09
    ç´«èī²
    -0.08
    .rmi
    -0.08
    大åĬĽæĶ¯æĮģ
    -0.08
    ç¹ģåįİ
    -0.08
    POSITIVE LOGITS
    æ³³
    0.20
    æ°´è´¨
    0.20
    æ°´ä¸Ń
    0.20
    æ°´åŁŁ
    0.18
    游泳
    0.18
     water
    0.18
    溺
    0.17
     водо
    0.17
    æ°´éĩı
    0.17
    æ°´ä¸Ĭ
    0.17
    Activations Density 0.098%

    No Known Activations