© 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. 62921
    Prev
    Next
    INDEX
    Explanations

    requires

    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
     wed
    -0.09
    æĺ¯ä¸įåı¯èĥ½
    -0.09
    .Cursor
    -0.09
    åĽĽä¸ªèĩªä¿¡
    -0.09
    çļĦåĬ¨ä½ľ
    -0.09
    å¤Ħåľ¨
    -0.09
    getResource
    -0.09
    äº¤æĽ¿
    -0.09
    æĢİä¹Īåı¯èĥ½
    -0.09
    ä¸į论æĺ¯
    -0.09
    POSITIVE LOGITS
    ä»į
    0.11
    èĵij
    0.10
    ä»įçĦ¶
    0.10
    ä¾ĿçĦ¶
    0.09
     jednak
    0.09
    ä»įå°Ĩ
    0.09
    åīįæıIJæĺ¯
    0.09
    ä»įæĺ¯
    0.09
    æ¯ķç«Łæĺ¯
    0.09
    ç»´ä¿®
    0.09
    Activations Density 0.209%

    No Known Activations