© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52474
    Prev
    Next
    INDEX
    Explanations

    indicates or suggests information

    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
    åķĨéĩı
    -0.09
    usta
    -0.09
    çıĪ
    -0.09
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    â¬ĩ
    -0.08
    ä¸İæŶ
    -0.08
    å°±æѤ
    -0.08
    æĥ³èµ·æĿ¥
    -0.08
    åĤħ
    -0.08
    é¹ij
    -0.08
    POSITIVE LOGITS
    itten
    0.08
    ãģĨ
    0.08
    èµ·ä¼ı
    0.08
    常å§Ķä¼ļ
    0.08
    马桶
    0.08
     licked
    0.08
     Noon
    0.08
    å¦Ĥä½ķåİ»
    0.08
    itta
    0.08
    icing
    0.08
    Activations Density 0.496%

    No Known Activations