© 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. 898
    Prev
    Next
    INDEX
    Explanations

    contractions and questions

    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
     ×Ĺ×ĵ
    -0.09
    çĢĽ
    -0.09
    flix
    -0.09
    çļĦä¸ľè¥¿
    -0.09
    ãģ¿ãģŁãģĦãģª
    -0.08
    ä¸ĢåŃĹ
    -0.08
     lắm
    -0.08
    _vlan
    -0.08
    _BUILD
    -0.08
    éĩį建
    -0.08
    POSITIVE LOGITS
    ãģĿãĤĮãģ«
    0.10
    yyy
    0.09
    èĩ´å¯Į
    0.08
    yy
    0.08
    æĪijçļĦå¿ĥ
    0.08
    wik
    0.08
    åŁºç¡Ģ设æĸ½
    0.08
    boost
    0.08
    æīĭèīº
    0.08
    éķ¿æķĪæľºåĪ¶
    0.08
    Activations Density 0.009%

    No Known Activations