© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52605
    Prev
    Next
    INDEX
    Explanations

    that are

    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
    æĺ¯ä¸Ģç§į
    -0.09
    عدد
    -0.09
    æĪIJ为ä¸ĢåIJį
    -0.09
    itative
    -0.09
    鸥
    -0.09
    idges
    -0.09
    ÑĢиÑģÑĤ
    -0.09
    burgh
    -0.08
    _Speed
    -0.08
    лаÑģ
    -0.08
    POSITIVE LOGITS
    便äºİ
    0.10
    ä½łåºĶ该
    0.10
    nap
    0.09
    åIJĬ顶
    0.09
    ä¼ļå½±åĵį
    0.09
    åĴĮåľ°åĮº
    0.09
    对该
    0.09
    ä½łä¼ļ
    0.09
    åĢ¼å¾Ĺåħ³æ³¨
    0.09
    anan
    0.08
    Activations Density 0.205%

    No Known Activations