© 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. 34279
    Prev
    Next
    INDEX
    Explanations

    musician, singer, artist, classical music

    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
    è§Ĥå½±
    -0.10
    é¢ģ
    -0.10
    è°Ĭ
    -0.09
     condol
    -0.09
    æĦıå¤ĸ
    -0.09
    èµĦæºIJéħįç½®
    -0.09
    åħ¢
    -0.09
    ç¼´è´¹
    -0.09
    ä¸ĩéĩĮ
    -0.09
    çĪ±å¿ĥ
    -0.09
    POSITIVE LOGITS
    ä¼łç»Ł
    0.15
    ä¼łç»ŁçļĦ
    0.11
    4
    0.11
    åĤ³çµ±
    0.11
    æĪıæĽ²
    0.11
    5
    0.10
    æ¼ĶåĶ±
    0.10
    åĶ±
    0.10
     traditional
    0.10
    ä¼łæī¿
    0.10
    Activations Density 0.068%

    No Known Activations