© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 58725
    Prev
    Next
    INDEX
    Explanations

    more space, than, peaceful, effective, sustainable, processing, dynamic, objective

    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
    æĸ°éĹ»ä¸Ńå¿ĥ
    -0.12
    è¯ļå®ŀ
    -0.10
    æ³°å±±
    -0.10
    é£ŀè¡Įåijĺ
    -0.09
    illard
    -0.09
    orado
    -0.09
    ADVERTISEMENT
    -0.09
    åIJĿ
    -0.09
    åºŃ
    -0.09
    å¸ĪåĤħ
    -0.09
    POSITIVE LOGITS
    æľįåĬ¡è´¨éĩı
    0.08
    ç½ķ
    0.08
    æĽ´å¥½åľ°
    0.08
    mart
    0.08
    éĻĮ
    0.08
    å¡ij
    0.08
    åĬłå¼ºå¯¹
    0.08
    Ãłi
    0.08
     Ùħج
    0.08
     eget
    0.08
    Activations Density 0.083%

    No Known Activations