© 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. 61596
    Prev
    Next
    INDEX
    Explanations

    to be or to have

    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
    人éĥ½
    -0.10
    åIJĦæł·
    -0.10
    åIJĦç§į
    -0.09
    å¼Ħ
    -0.08
     заг
    -0.08
    ðŁı»
    -0.08
    åħ¬åı¸å°Ĩ
    -0.08
    佬
    -0.08
    è°ĥèĬĤ
    -0.08
    éĺħ读
    -0.08
    POSITIVE LOGITS
     бÑĭÑĤÑĮ
    0.11
    æĺ¯ä¸Ģ件
    0.11
     byÄĩ
    0.10
    æĺ¯åľ¨
    0.10
     ÑıвлÑı
    0.10
    /th
    0.10
    æĪIJ为
    0.09
    æĺ¯ä¸Ģ
    0.09
    æĺ¯æĪij们
    0.09
    æĺ¯ä¸Ģ项
    0.09
    Activations Density 0.136%

    No Known Activations