© 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. 47656
    Prev
    Next
    INDEX
    Explanations

    often complain of symptoms

    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
    Negative Logits
     Already
    -0.10
    ä»ħæľī
    -0.10
    ä»ĸå·²ç»ı
    -0.10
    abar
    -0.09
    Already
    -0.09
     already
    -0.09
    å·²ç»ıå¼Ģå§ĭ
    -0.09
    å·²ç»ıåľ¨
    -0.08
    就已ç»ı
    -0.08
    _already
    -0.08
    POSITIVE LOGITS
    å¾Ģå¾Ģ
    0.34
    å¾Ģå¾Ģæĺ¯
    0.30
     often
    0.29
    éĢļ常
    0.28
    éĢļ常æĺ¯
    0.28
    å¾Ģå¾Ģä¼ļ
    0.27
     usually
    0.26
    大å¤ļ
    0.26
    ä¸ĢèĪ¬éĥ½æĺ¯
    0.25
    å¾Īå¤ļæŶåĢĻ
    0.25
    Activations Density 0.568%

    No Known Activations