© 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. 31480
    Prev
    Next
    INDEX
    Explanations

    ask permission before

    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
     Spicer
    -0.09
    æ¿ł
    -0.08
    UTE
    -0.08
    æĦŁåºĶ
    -0.08
    é¢Ŀ
    -0.08
    flash
    -0.08
    æ°®
    -0.08
    ute
    -0.08
    ä¼ij
    -0.08
    çºłæŃ£
    -0.08
    POSITIVE LOGITS
    奥æŀĹåĮ¹åħĭ
    0.09
    æľ¬åĽ½
    0.09
     counterfeit
    0.09
    ì²Ļ
    0.09
    ä»ĬçĶŁ
    0.09
    éŨæĪ·ç½ijç«Ļ
    0.09
    è¿Ļ个èģĮä¸ļ
    0.09
    绣
    0.09
    è¶ĭ
    0.08
    åħ·ä½ĵçļĦ
    0.08
    Activations Density 0.021%

    No Known Activations