© 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. 48188
    Prev
    Next
    INDEX
    Explanations

    musicians and conductors

    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´º
    -0.11
    åĿļåĽº
    -0.09
    éķ¿å¯¿
    -0.09
    åĿļ强
    -0.09
    åı£æ°´
    -0.08
    ç«ŀäºīä¼ĺåĬ¿
    -0.08
    è´Ŀå°Ķ
    -0.08
    éĺĸ
    -0.08
    åįģéĩĮ
    -0.08
     Wilkinson
    -0.08
    POSITIVE LOGITS
    exas
    0.10
    æĩĤå¾Ĺ
    0.09
    alem
    0.09
     Exc
    0.09
    è¯Ħå§Ķ
    0.08
    conduct
    0.08
     conductor
    0.08
    å¥ı
    0.08
    æĸ¥
    0.08
    à¸į
    0.08
    Activations Density 0.039%

    No Known Activations