© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20479
    Prev
    Next
    INDEX
    Explanations

    sitting

    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
    åĿĢ
    -0.11
    ï¸ı
    -0.09
    /remove
    -0.09
     Sat
    -0.09
    (es
    -0.09
    ÙĪار
    -0.09
    主æĦı
    -0.09
    òng
    -0.09
     sat
    -0.08
    ä¸Ģ举
    -0.08
    POSITIVE LOGITS
     Ritch
    0.09
    è¶Ĭ好
    0.08
    æĢİä¹Īåı¯èĥ½
    0.08
    reich
    0.08
    æĹłè¾ľ
    0.08
    lp
    0.08
    OptionsMenu
    0.08
    gé
    0.08
    atism
    0.08
    ç»IJ
    0.08
    Activations Density 0.013%

    No Known Activations