© 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. 53281
    Prev
    Next
    INDEX
    Explanations

    pre-colonial, pre-Columbian

    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
    æİĴåIJį第ä¸Ģ
    -0.10
     Äiju
    -0.09
    éĹ
    -0.09
    çļĦç»ıéªĮ
    -0.09
    ä¸įå®Į
    -0.09
    ãĥ©ãĥ³ãĤ¹
    -0.09
    _FLAGS
    -0.09
    	union
    -0.09
    _sk
    -0.09
    æ³¾
    -0.09
    POSITIVE LOGITS
     capitals
    0.10
    éģĹåĿĢ
    0.09
    .pag
    0.09
    åŀ®
    0.09
    çŁ³å®¶
    0.09
     Belt
    0.09
    æĮģ
    0.08
    鱿
    0.08
    -ending
    0.08
    建éĢł
    0.08
    Activations Density 0.069%

    No Known Activations