© 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. 26142
    Prev
    Next
    INDEX
    Explanations

    from a or an

    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
    æĿ¥èĩª
    -0.13
    äºĽä»Ģä¹Ī
    -0.10
    ä¸Ńåħ³æĿij
    -0.10
    ä»İä¸Ń
    -0.10
    æĿ¥èĩªäºİ
    -0.09
    ä»İäºĭ
    -0.09
     gì
    -0.09
    dorf
    -0.09
    ä»İ
    -0.09
     ÙħÙĨ
    -0.09
    POSITIVE LOGITS
    /to
    0.15
     afar
    0.13
    ä¸Ģå¼Ģå§ĭ
    0.13
     standpoint
    0.12
     scratch
    0.12
    ench
    0.10
    侧éĿ¢
    0.10
    没è§ģè¿ĩ
    0.09
    ä¸Ģå¼Ģå§ĭå°±
    0.09
    ä¸ī个æĸ¹éĿ¢
    0.09
    Activations Density 0.052%

    No Known Activations