© 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. 39512
    Prev
    Next
    INDEX
    Explanations

    pro-life advocates

    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
    å¼ĢæľĹ
    -0.12
    笳
    -0.10
    å·¥å§Ķ
    -0.10
    inka
    -0.10
    èĹı
    -0.09
    æĢĨ
    -0.09
    å¦Ĥæŀľä¸įæĺ¯
    -0.09
    é¢ĸ
    -0.09
    èĩªåıij
    -0.09
    èĩªè´Ł
    -0.08
    POSITIVE LOGITS
    (blob
    0.09
    vox
    0.09
    éĻIJå®ļ
    0.09
     Ñģог
    0.09
    æ¯ı次
    0.09
    ÑģÑĤво
    0.08
    bam
    0.08
    BLEM
    0.08
    èµĬ
    0.08
    æ¯ıä¸Ģ次
    0.08
    Activations Density 0.105%

    No Known Activations