© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40293
    Prev
    Next
    INDEX
    Explanations

    ASP.NET web development technologies

    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
    Negative Logits
    paque
    -0.08
    ment
    -0.08
     salv
    -0.08
    ney
    -0.08
    对èĩªå·±
    -0.08
    лиÑĨ
    -0.08
     ведÑĮ
    -0.08
    andon
    -0.08
    åĬ¿
    -0.08
    ÙĪار
    -0.08
    POSITIVE LOGITS
    arius
    0.10
    olio
    0.09
    è¿ĻçĤ¹
    0.09
    ä¸Ģ头
    0.09
    循çݯç»ıæµİ
    0.08
    人éĥ½
    0.08
    ripper
    0.08
    çªł
    0.08
    ç«łç¨ĭ
    0.08
    orian
    0.08
    Activations Density 0.258%

    No Known Activations