© 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. 35796
    Prev
    Next
    INDEX
    Explanations

    the way

    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
    uke
    -0.10
    woods
    -0.09
    enties
    -0.09
    ç»ĵå®ŀ
    -0.08
    partners
    -0.08
    æīĵåĩ»
    -0.08
    æªĢ
    -0.08
    iten
    -0.08
    -double
    -0.08
     Blonde
    -0.08
    POSITIVE LOGITS
     way
    0.19
    æĸ¹å¼ı
    0.13
    çļĦæĸ¹å¼ı
    0.12
    way
    0.12
    ãĤĪãģĨãģ«
    0.12
    è¿Ļç§įæĸ¹å¼ı
    0.12
     Way
    0.12
     WAY
    0.11
     ways
    0.11
    æĸ¹éĿ¢
    0.11
    Activations Density 0.064%

    No Known Activations