© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52949
    Prev
    Next
    INDEX
    Explanations

    analytical mind, poet laureate, diary/adventures

    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
    æŶæĬ¥
    -0.10
    ä¾ĭè¡Į
    -0.09
    mart
    -0.09
    çļĦåij½è¿IJ
    -0.09
    åĬŀçIJĨ
    -0.09
    æķijåij½
    -0.09
    åºľ
    -0.09
    Authors
    -0.08
    åı°ä¸Ĭ
    -0.08
     proced
    -0.08
    POSITIVE LOGITS
    妹
    0.10
    羸
    0.10
    è´¨çĸij
    0.09
    é¢ĦæĬ¥
    0.09
    åľ°åĿĹ
    0.09
    ãģ¨ãģĨ
    0.09
    表æĥħ
    0.08
    thesis
    0.08
    baugh
    0.08
    .LinkedList
    0.08
    Activations Density 0.163%

    No Known Activations