© 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. 58837
    Prev
    Next
    INDEX
    Explanations

    professors teachers managers and other authority figures

    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
    ç»ĻåĪ«äºº
    -0.11
    æ¡£
    -0.09
    efore
    -0.09
    æĮ£æīİ
    -0.09
    ometry
    -0.08
    é»į
    -0.08
    份
    -0.08
    æłĢ
    -0.08
    unch
    -0.08
    åĩĢåĮĸ
    -0.08
    POSITIVE LOGITS
    å¨ĺ
    0.10
    ëĭĺ
    0.09
    å¨
    0.09
    大人
    0.08
    ouri
    0.08
    æĭ³å¤´
    0.08
    amil
    0.08
    满æĦıçļĦ
    0.08
    lyn
    0.08
    ç²¹
    0.08
    Activations Density 0.056%

    No Known Activations