© 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. 49566
    Prev
    Next
    INDEX
    Explanations

    routinely/regularly/frequently + action

    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
    å¾Īåı¯èĥ½
    -0.11
    责任åĪ¶
    -0.10
    çĶŁæ´»æĸ¹å¼ı
    -0.10
    å§ĭç»ĪåĿļæĮģ
    -0.10
    äºĽè®¸
    -0.09
    ä¼ĹæīĢ
    -0.09
    ç»Ī究
    -0.09
    æĥ³äºĨæĥ³
    -0.09
    主è¦ģæĺ¯
    -0.09
    æľīä¸ĢçĤ¹
    -0.09
    POSITIVE LOGITS
    ouro
    0.11
    éģŃåĪ°
    0.10
    ä½İäºİ
    0.10
     Tops
    0.09
    被人
    0.09
    宿
    0.09
    éĿ¢ä¸´çĿĢ
    0.09
    hte
    0.09
    åıĹåĪ°
    0.09
    éı¡
    0.09
    Activations Density 0.030%

    No Known Activations