© 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. 31201
    Prev
    Next
    INDEX
    Explanations

    since the

    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
    ç²īæľ«
    -0.09
    atak
    -0.09
    åīįæĸ¹
    -0.08
    æĢĿç´¢
    -0.08
    ç§ģç«ĭ
    -0.08
    ording
    -0.08
    ç´§å¯Ĩç»ĵåIJĪ
    -0.08
    iones
    -0.08
     Wallace
    -0.08
     sant
    -0.08
    POSITIVE LOGITS
    éĤ£æ¬¡
    0.10
     Adoption
    0.09
    享åıĹåĪ°
    0.09
    æľĢåIJİä¸Ģ次
    0.09
    åIJ¬è¿ĩ
    0.09
    éĥĩ
    0.09
    å®Ŀè´µçļĦ
    0.09
    èĩ³ä»Ĭ
    0.09
    ä¸ĭä¸Ģç¯ĩ
    0.09
    é¢Ĩ
    0.09
    Activations Density 0.052%

    No Known Activations