© 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. 23536
    Prev
    Next
    INDEX
    Explanations

    sentence-ending punctuation

    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
    SCO
    -0.09
    ä¸įç»ı
    -0.09
     Fro
    -0.08
     bench
    -0.08
    æĺ¥ç§ĭ
    -0.08
     Vul
    -0.08
    é¢ĩ
    -0.08
    Tro
    -0.08
    creen
    -0.08
    æĻļéĹ´
    -0.08
    POSITIVE LOGITS
    åĽłä¸ºä»ĸ
    0.12
    åĽłä¸ºä»ĸ们
    0.11
    è¿Ļæĺ¯åĽłä¸º
    0.10
    åĽłä¸ºåľ¨
    0.10
    èĪ¬çļĦ
    0.09
    alm
    0.09
    olas
    0.09
    åĽłåħ¶
    0.09
    æģ¨ä¸įå¾Ĺ
    0.09
    åĽłä¸ºå®ĥ
    0.09
    Activations Density 0.186%

    No Known Activations