© 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. 39498
    Prev
    Next
    INDEX
    Explanations

    manner of occurrence

    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
     undo
    -0.08
    BM
    -0.08
    cul
    -0.08
     Dare
    -0.08
    itr
    -0.08
    ayers
    -0.07
    drv
    -0.07
    è°¯
    -0.07
    ãģĦãģ¦ãģĦãĤĭ
    -0.07
     conditional
    -0.07
    POSITIVE LOGITS
    æĸ¹å¼ı
    0.14
    åĮĨ
    0.12
    è¿Ļç§įæĸ¹å¼ı
    0.11
    æĺ¯åĽłä¸º
    0.11
    被åĬ¨
    0.11
    æĸ¹å¼ıè¿Ľè¡Į
    0.11
    çļĦæĸ¹å¼ı
    0.11
    èĢ»
    0.11
    æļ´åĬĽ
    0.10
    æģ¨
    0.10
    Activations Density 0.232%

    No Known Activations