© 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. 48314
    Prev
    Next
    INDEX
    Explanations

    situation or scenario

    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
    uw
    -0.11
    ãģ»ãģĨ
    -0.11
    éĤ£ä»½
    -0.10
    é¦Ĵ
    -0.10
    agas
    -0.09
    Lifetime
    -0.09
    奥æŀĹåĮ¹
    -0.09
    è¿Ļ个èģĮä¸ļ
    -0.09
    ä»ĸçŁ¥éģĵ
    -0.09
    åİĦ
    -0.09
    POSITIVE LOGITS
     Situation
    0.10
     situation
    0.10
    æ¸ħæĻ¨
    0.10
     ÑģиÑĤÑĥаÑĨиÑı
    0.10
    åľºæĻ¯
    0.09
    scene
    0.09
    çļĦæĥħå½¢
    0.09
    åĩĮæĻ¨
    0.09
    æĥħå½¢
    0.08
    æŃ£åĢ¼
    0.08
    Activations Density 0.111%

    No Known Activations