© 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. 21438
    Prev
    Next
    INDEX
    Explanations

    Disney, movie, film, Class, Cruise

    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
    uario
    -0.10
     ÐłÐ¾Ñģ
    -0.09
    ogh
    -0.09
    sWith
    -0.09
    åIJİæŀľ
    -0.09
     unspecified
    -0.09
    rieve
    -0.09
     Admir
    -0.08
    uffman
    -0.08
     двигаÑĤ
    -0.08
    POSITIVE LOGITS
    .createClass
    0.09
    tron
    0.09
    æĸĽ
    0.08
    piration
    0.08
    æıIJ款
    0.08
     اÙĦÙĨÙģس
    0.08
    tran
    0.08
    yü
    0.08
    ãģªãĤĬ
    0.08
    èººåľ¨åºĬä¸Ĭ
    0.08
    Activations Density 0.008%

    No Known Activations