© 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. 51798
    Prev
    Next
    INDEX
    Explanations

    porn, stars

    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
    çĪ±ç¾İ
    -0.09
    ÑģÑĤолÑĮ
    -0.08
    Advertisements
    -0.08
    åıĸè¯ģ
    -0.08
    èłķ
    -0.08
    ç²¾åįİ
    -0.08
    åIJ¬è¯Ŀ
    -0.08
    COVERY
    -0.08
    æī¾åĩº
    -0.08
    åıįè¿ĩæĿ¥
    -0.08
    POSITIVE LOGITS
     archival
    0.09
    èģŀ
    0.08
    æĭĴ
    0.08
    istar
    0.08
    éĥ¨éŨ
    0.08
    ä¸Ģéģĵ
    0.08
    çµĦ
    0.08
    Translator
    0.08
    ész
    0.08
    wear
    0.08
    Activations Density 0.057%

    No Known Activations