© 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. 26876
    Prev
    Next
    INDEX
    Explanations

    forum discussions or rules

    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
    -0.10
    burg
    -0.09
    IMUM
    -0.08
     Gaul
    -0.08
    coat
    -0.08
     Ñģобой
    -0.08
     Gott
    -0.08
     اÙĦدÙĨÙĬا
    -0.08
    ä¹į
    -0.07
    orem
    -0.07
    POSITIVE LOGITS
    spo
    0.11
    ships
    0.11
    ç²¾åįİ
    0.11
    éĩĮçļĦ
    0.10
    æĪIJç«ĭ以æĿ¥
    0.10
    otion
    0.10
    matic
    0.10
    ÑĢ
    0.10
    åĨħçļĦ
    0.10
    大èĥĨ
    0.10
    Activations Density 0.017%

    No Known Activations