© 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. 19344
    Prev
    Next
    INDEX
    Explanations

    subtitle, dubbed, captions, interpreter

    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
    ively
    -0.10
    ä¸į顾
    -0.09
    ÎĬ
    -0.09
    _NM
    -0.09
    å°¼æĸ¯
    -0.09
    nam
    -0.09
    æŁ½
    -0.09
    à¹Į
    -0.09
    ä¿¡æģ¯åħ¬å¼Ģ
    -0.09
    æľ¬çĿĢ
    -0.08
    POSITIVE LOGITS
    åĽŀåIJĪ
    0.09
    è·Ĺ
    0.09
    ÙĦغ
    0.09
    cts
    0.09
    Wars
    0.09
    é¹Ħ
    0.08
    ÑĪка
    0.08
    urette
    0.08
    çİĭæľĿ
    0.08
    -equipped
    0.08
    Activations Density 0.004%

    No Known Activations