© 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. 58263
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by names/words

    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
    鹧
    -0.10
    è°±åĨĻ
    -0.10
    èĮĦ
    -0.10
    并éĿŀ
    -0.10
    è¿ijäºĽ
    -0.09
    æĪĸå°Ĩ
    -0.09
    èĤ´
    -0.09
    Ø«ÙĦ
    -0.08
    好象
    -0.08
    çļĦä¸Ģ项
    -0.08
    POSITIVE LOGITS
    éģĤ
    0.09
    说çĿĢ
    0.09
    sap
    0.08
    说å®Į
    0.08
    æ¯Ĵ
    0.08
    ä»ĸ说
    0.08
    ä½łçİ°åľ¨
    0.08
    åĨħéĥ¨æݧåĪ¶
    0.08
    isko
    0.08
    .Constants
    0.08
    Activations Density 0.038%

    No Known Activations