© 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. 35037
    Prev
    Next
    INDEX
    Explanations

    seriously or "serious"

    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
    æĺİæĺİ
    -0.11
    好象
    -0.11
    æ·ĭ
    -0.10
    æ¥Ķ
    -0.10
    è¿ĺå¾Ĺ
    -0.09
    åħľ
    -0.09
    çīºçī²
    -0.09
    åħ¨æ°ij
    -0.09
    庶
    -0.09
    ä»Ģä¹Īéĥ½
    -0.09
    POSITIVE LOGITS
     kidding
    0.13
    å¼Ģçİ©ç¬ij
    0.13
    Seriously
    0.12
    çİ©ç¬ij
    0.12
     Seriously
    0.11
     joke
    0.10
    è°ĥä¾ĥ
    0.10
    è¯ļæĦı
    0.09
     joking
    0.09
    æĪı
    0.09
    Activations Density 0.054%

    No Known Activations