© 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. 55116
    Prev
    Next
    INDEX
    Explanations

    but, unfortunately, regret, declines

    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
    榴
    -0.09
    aravel
    -0.08
    æ¹ĺ
    -0.08
    滩
    -0.08
    çļĦåŃ©åŃIJ
    -0.08
    lood
    -0.08
    rai
    -0.08
    ä¸ŃèĢĥ
    -0.08
    Gar
    -0.08
    onta
    -0.08
    POSITIVE LOGITS
    bots
    0.10
    çĥ
    0.09
    æģIJæĢķ
    0.09
    æĬĢæľ¯æĶ¯æĮģ
    0.09
    ãģķãģĦ
    0.09
    è¿Ļ个æŶåĢĻ
    0.09
    æīįçŁ¥éģĵ
    0.09
    å®ŀåľ¨å¤ª
    0.09
    强è¡Į
    0.09
    ä¸įåIJĮæĦı
    0.09
    Activations Density 0.026%

    No Known Activations