© 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. 16836
    Prev
    Next
    INDEX
    Explanations

    recalling past events or feelings

    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
    è°ģçŁ¥éģĵ
    -0.11
    æĬij
    -0.10
    èĤ²åĦ¿
    -0.10
    çłĿ
    -0.10
    ç»ıèIJ¥æ¨¡å¼ı
    -0.09
    ä¸įæİĴéĻ¤
    -0.09
    åIJĮèĥŀ
    -0.09
    ä¸īçĻ¾
    -0.09
    çİ®
    -0.09
    å«©
    -0.09
    POSITIVE LOGITS
    å¾Īæ¸ħæ¥ļ
    0.09
    é«ĺ强度
    0.08
     being
    0.08
    æľī个
    0.08
     feeling
    0.08
     Feeling
    0.08
    æľī人
    0.08
    enty
    0.08
    ard
    0.07
    æľīä¸Ģ
    0.07
    Activations Density 0.010%

    No Known Activations