© 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. 54188
    Prev
    Next
    INDEX
    Explanations

    NASCAR, Xamarin, cross-country skiing

    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
    OrCreate
    -0.10
    æ»ĭ
    -0.09
    ogens
    -0.09
    ogen
    -0.09
    uger
    -0.09
    糧
    -0.08
    ç¼¥
    -0.08
     Ult
    -0.08
    rix
    -0.08
     fer
    -0.08
    POSITIVE LOGITS
    å¾Ĺä½ı
    0.09
    inality
    0.09
    æīķ
    0.09
    ¿
    0.09
    ÑģеÑĤ
    0.09
    é²ľæĺİ
    0.09
    ä¸ĢæĹ¥
    0.09
    ä¸Ģ级
    0.09
     gdk
    0.09
     пеÑĢвой
    0.09
    Activations Density 0.001%

    No Known Activations