© 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. 5415
    Prev
    Next
    INDEX
    Explanations

    contract or agreement

    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
    æıIJæ¡Ī
    -0.09
    æĬĵ好
    -0.08
    å»·
    -0.08
    STRUCTOR
    -0.08
    rac
    -0.08
    æĬ¥éģĵ
    -0.08
    fine
    -0.08
    ä¸ĭãģĴ
    -0.08
    åĢ¡è®®
    -0.08
    主æĦı
    -0.08
    POSITIVE LOGITS
    约å®ļ
    0.13
    æľ¬ç½ij
    0.11
    笨
    0.10
    çļĦåĨħ容
    0.10
     agreements
    0.09
    ile
    0.09
    åĮ»ç§ij
    0.09
    /live
    0.09
    éļIJ约
    0.09
    ä½ľåĵģåĨħ容
    0.08
    Activations Density 0.085%

    No Known Activations