© 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. 55003
    Prev
    Next
    INDEX
    Explanations

    have every / whoever / two / your / a / one / music

    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
    åıĪ被
    -0.09
    wr
    -0.09
    åħ¨æĹ¥
    -0.08
    ç«Łæĺ¯
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    对æīĭ
    -0.08
    ä¹ĸ
    -0.08
     Brend
    -0.08
    aurus
    -0.08
    ç²³
    -0.08
    POSITIVE LOGITS
    ä¸ĵ人
    0.10
    -sheet
    0.09
    hoff
    0.09
    ç¨ĭ度
    0.09
    annel
    0.09
    å®´ä¼ļ
    0.09
    èĬ±å¼Ģ
    0.09
    æĮ¯ãĤĬ
    0.09
    ç°ĩ
    0.09
    åĮºåŁŁåĨħ
    0.08
    Activations Density 0.165%

    No Known Activations