© 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. 37626
    Prev
    Next
    INDEX
    Explanations

    that ... may

    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
    å¾Īå·®
    -0.10
    马ä¸Ĭå°±
    -0.09
    å°±è¦ģ
    -0.09
    éļıæĦı
    -0.09
    äºĨå¾Īå¤ļ
    -0.09
    __.__
    -0.09
    cord
    -0.08
     ÑĤоже
    -0.08
    大家éĥ½
    -0.08
    åIJĦæł·
    -0.08
    POSITIVE LOGITS
    ç»®
    0.09
    åı¯èĥ½
    0.09
    æĢµ
    0.09
    主管
    0.09
    propri
    0.08
    èIJĿ
    0.08
    åı¯èĥ½åĩºçİ°
    0.08
    ä¸į便
    0.08
    æłı
    0.08
    èĥĮ
    0.08
    Activations Density 0.022%

    No Known Activations