© 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. 51375
    Prev
    Next
    INDEX
    Explanations

    explanation, basis, or introduction

    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
    ä½ľæģ¯
    -0.10
    è¿Īåĩº
    -0.09
    çİĩ为
    -0.09
    anto
    -0.09
    ä¸Ģè§Ī
    -0.09
    å¨ģå°Ķ
    -0.08
    .sg
    -0.08
    _OPTS
    -0.08
    ãģĵãģ¨ãģ¯
    -0.08
    åľ¨ç¾İåĽ½
    -0.08
    POSITIVE LOGITS
    åįģ足
    0.10
    èIJ¥éĢł
    0.09
    æĮģæľī人
    0.08
    缴è¾ĸå¸Ĥ
    0.08
     mund
    0.08
    arith
    0.08
    æľīæľºä¼ļ
    0.08
     giảng
    0.08
    ä¸įæ¸ħ
    0.08
     ÑģозданиÑı
    0.08
    Activations Density 0.126%

    No Known Activations