© 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. 1447
    Prev
    Next
    INDEX
    Explanations

    content ownership and rights

    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
    次ä¼ļè®®
    -0.10
    argas
    -0.09
    usta
    -0.09
    ç³Ļ
    -0.09
    åĹħ
    -0.09
     ÙħÙĤابÙĦ
    -0.08
    è¿ĻäºĽäºº
    -0.08
    赶
    -0.08
    ä¾Ŀæ³ķ追究
    -0.08
     Patch
    -0.08
    POSITIVE LOGITS
    è§Ĥä¼Ĺ
    0.11
     audience
    0.10
    äºĴåĬ¨
    0.10
     Audience
    0.10
    篦
    0.08
    æĬĬæīĭ
    0.08
    cord
    0.08
    GIN
    0.08
     interact
    0.08
    èŀįåħ¥
    0.08
    Activations Density 0.038%

    No Known Activations