© 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. 2839
    Prev
    Next
    INDEX
    Explanations

    bills and data

    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
    ORIZ
    -0.13
    edx
    -0.09
    ç»Ŀ
    -0.09
    Çļ
    -0.09
    è¶ĬæĿ¥
    -0.09
    mys
    -0.09
    ãģ¨ãģĦ
    -0.09
    OKEN
    -0.09
    éĥĩ
    -0.09
    éħ½
    -0.09
    POSITIVE LOGITS
    å¸Ń
    0.09
    herent
    0.09
    æѤæĸĩ
    0.09
     Coc
    0.08
    isses
    0.08
    æĬĬè¿ĻäºĽ
    0.08
    们
    0.08
     ×IJ׾×Ķ
    0.08
    使ä¹ĭ
    0.08
     Near
    0.08
    Activations Density 0.766%

    No Known Activations