© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20865
    Prev
    Next
    INDEX
    Explanations

    names of people, places, or organizations

    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
    çİŁ
    -0.11
    çī©èµĦ
    -0.09
    çīĮ
    -0.09
    tes
    -0.09
    hum
    -0.09
    æ»ŀ
    -0.09
    éĥ´å·ŀ
    -0.09
    claimer
    -0.09
    æĬ¹
    -0.09
    eroon
    -0.08
    POSITIVE LOGITS
    ç¾İåĽ½äºº
    0.08
    Tube
    0.08
     Vect
    0.08
    èģĮä¸ļæĬĢæľ¯
    0.08
     Pars
    0.08
    год
    0.08
    /posts
    0.08
    .BO
    0.08
    è¦ģåľ¨
    0.08
    éķĹ
    0.07
    Activations Density 0.094%

    No Known Activations