© 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. 11550
    Prev
    Next
    INDEX
    Explanations

    enjoying positive moments

    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
    åĬ¨èĥ½
    -0.09
    庶
    -0.09
    åįĹåĮĹ
    -0.09
     CS
    -0.09
     Toy
    -0.08
    ç«Ļç«ĭ
    -0.08
    åIJ¬å¾Ĺ
    -0.08
    衲
    -0.08
    èĥĮä¸Ĭ
    -0.08
     Physics
    -0.08
    POSITIVE LOGITS
    享åıĹ
    0.13
    秦çļĩ
    0.13
    è¿ĩç¨ĭ
    0.12
    夹
    0.11
    éģİç¨ĭ
    0.11
    çīĮ
    0.11
    éļ¾å¾Ĺ
    0.10
    çıįæĥľ
    0.10
    æĬĵ
    0.10
     Enjoy
    0.09
    Activations Density 0.036%

    No Known Activations