© 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. 39094
    Prev
    Next
    INDEX
    Explanations

    immigration and arrivals

    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¦ģå¿Į
    -0.11
    æĭĸ
    -0.10
    å¼Ģåĩº
    -0.09
    æİĸ
    -0.09
    çŃ¹
    -0.09
    èij
    -0.09
    åݻ买
    -0.09
    综åIJĪæķ´æ²»
    -0.09
    èĪĨ
    -0.08
    æ»´
    -0.08
    POSITIVE LOGITS
    .delegate
    0.10
    éĢĹ
    0.09
    大åħ¨
    0.09
    èĩªåľ¨
    0.09
    人äºĭ
    0.09
    åı£å²¸
    0.09
    MLE
    0.09
    çĿ¥
    0.09
    ç²ĺ
    0.09
    ä½IJ
    0.09
    Activations Density 0.100%

    No Known Activations