© 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. 1778
    Prev
    Next
    INDEX
    Explanations

    maximizing returns or company performance

    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
    è´¼
    -0.10
    åĽ½æ°ij
    -0.09
    è´«
    -0.08
    æ°ijéĹ´
    -0.08
    erto
    -0.08
    夤
    -0.08
    å¿ĹæĦ¿
    -0.08
    ersistence
    -0.08
    èµ·çłģ
    -0.08
    åĴĸ
    -0.08
    POSITIVE LOGITS
    让æĤ¨
    0.10
    æĸ¹æ¡Ī
    0.10
    æĤ¨çļĦ
    0.10
    客æĪ·çļĦ
    0.10
    éĥ½å¸Ĥ
    0.09
    客æĪ·æıIJä¾Ľ
    0.09
    é«ĺæĸ°æĬĢæľ¯
    0.08
    ç¬ij容
    0.08
    åĩºèĩª
    0.08
     ÐĴаÑĪ
    0.08
    Activations Density 0.138%

    No Known Activations