© 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. 7298
    Prev
    Next
    INDEX
    Explanations

    everyone's or is

    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
    æľ¬äºº
    -0.10
    ä¸Ģ举
    -0.09
    ÙĨÙĪ
    -0.08
    ish
    -0.08
    é¥ŃåºĹ
    -0.08
    åĴĮä»ĸçļĦ
    -0.08
    ç§įç±»
    -0.08
    ä¸ĢæŃ¥æŃ¥
    -0.08
    æ¯ı
    -0.07
    ç§įç§į
    -0.07
    POSITIVE LOGITS
     гол
    0.10
    æ¾į
    0.10
    obl
    0.10
    缸çĪ±
    0.10
    aved
    0.10
    htable
    0.09
     else
    0.09
    è¤IJ
    0.09
    миÑĢ
    0.09
    è°ı
    0.09
    Activations Density 0.031%

    No Known Activations