© 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. 5346
    Prev
    Next
    INDEX
    Explanations

    alternatives or additions

    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
    èĪįå¾Ĺ
    -0.09
    åĪ°åºķ
    -0.09
    ä¸įåĨįæĺ¯
    -0.08
    鸾
    -0.08
    spo
    -0.08
    ä¸įä»ħ
    -0.08
    éĻ¡
    -0.08
    æĥħ人
    -0.08
     not
    -0.08
    yal
    -0.08
    POSITIVE LOGITS
    å¹²èĦĨ
    0.10
    è¿Ļç§įæĸ¹å¼ı
    0.10
    è¾ķ
    0.10
    ä»Ģä¹Īéĥ½ä¸į
    0.09
    ç§ijæĬĢèĤ¡ä»½
    0.09
     vic
    0.09
    åİ»æī¾
    0.09
     пÑĢоÑģÑĤо
    0.09
    转身
    0.09
    éĽĨåĽ¢èĤ¡ä»½
    0.09
    Activations Density 0.050%

    No Known Activations