© 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. 34042
    Prev
    Next
    INDEX
    Explanations

    musical instruments and performers

    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
     Squ
    -0.09
    unta
    -0.08
    icom
    -0.08
    æĿĥçĽĬ
    -0.08
    éré
    -0.08
    æł·çļĦ
    -0.08
    baum
    -0.08
    conti
    -0.08
     Silence
    -0.08
    _sq
    -0.08
    POSITIVE LOGITS
    åĮ¹
    0.09
    èĩ§
    0.09
    çľ¼çķĮ
    0.09
    åIJĮå¿Ĺ们
    0.09
    è¤IJ
    0.09
    å¿Į
    0.09
     trib
    0.09
    .Dense
    0.08
    æ´ĭæ´ĭ
    0.08
     Marvin
    0.08
    Activations Density 0.023%

    No Known Activations