© 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. 10874
    Prev
    Next
    INDEX
    Explanations

    interpretation, formation, method, decisions, activities, image

    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
    åĶ§
    -0.09
    овал
    -0.09
    STER
    -0.09
    èķ¾
    -0.08
    æѧ
    -0.08
    TRAN
    -0.08
    é»ĺ
    -0.08
    丹
    -0.08
    stands
    -0.08
    ìĨĮ
    -0.08
    POSITIVE LOGITS
    姿åĬ¿
    0.11
    æݪ
    0.10
    ä¸Ńå°ıåŀĭ
    0.09
    æĹ¶æľº
    0.09
    gar
    0.09
    è¿ĻäºĽéĹ®é¢ĺ
    0.09
    èģĶ
    0.09
    jdk
    0.08
    /right
    0.08
    åĽ´
    0.08
    Activations Density 0.161%

    No Known Activations