© 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. 34754
    Prev
    Next
    INDEX
    Explanations

    running

    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
    çıł
    -0.11
     Winn
    -0.08
    ardo
    -0.08
    å¸ľ
    -0.08
     Northwestern
    -0.08
    .TestCase
    -0.08
    _TBL
    -0.08
    æĬĢèīº
    -0.08
    æ¯ıä¸Ģ次
    -0.08
    æŃī
    -0.08
    POSITIVE LOGITS
    è¿IJ转
    0.20
    è¿IJè¡Į
    0.16
    è¿IJä½ľ
    0.15
    è¿IJèIJ¥
    0.11
     functioning
    0.11
    éģĭ
    0.10
    ä¸ĩçī©
    0.10
    é»ı
    0.10
    ä¸įåģľ
    0.10
    ç»´æĮģ
    0.10
    Activations Density 0.077%

    No Known Activations