© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51905
    Prev
    Next
    INDEX
    Explanations

    university names and affiliations

    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
    ä¸Ŀä¸Ŀ
    -0.10
     ÑĢаÑģÑĤвоÑĢ
    -0.09
    æģĭæĥħ
    -0.09
    顺
    -0.09
     MLM
    -0.08
     ÑĢеж
    -0.08
    ĮĢ
    -0.08
     Levi
    -0.08
    ois
    -0.08
    课åłĤ
    -0.08
    POSITIVE LOGITS
    æĭĽ
    0.09
    欣
    0.09
    CAF
    0.09
    oug
    0.09
     TAR
    0.08
    éĢīåĩº
    0.08
    åīį身
    0.08
    çķĻä½ı
    0.08
    assa
    0.08
    åĵ½
    0.08
    Activations Density 0.036%

    No Known Activations