© 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. 39068
    Prev
    Next
    INDEX
    Explanations

    for dummies

    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
    åºĶä»ĺ
    -0.09
    rier
    -0.09
    swer
    -0.09
    ishments
    -0.09
    oard
    -0.09
    riers
    -0.08
    ÑĢабоÑĤаÑĤÑĮ
    -0.08
    CartItem
    -0.08
    _pc
    -0.08
    claimer
    -0.08
    POSITIVE LOGITS
    æĪIJåijĺåįķä½į
    0.10
    说æĺİ书
    0.09
    å¯Ĥå¯ŀ
    0.09
    ä¸įå°ıå¿ĥ
    0.08
    fax
    0.08
    çľ¼çIJĥ
    0.08
    ges
    0.08
    çļĦ姿æĢģ
    0.08
    é«ĺçŃīéĻ¢æł¡
    0.08
    ä»Ģä¹Īåij¢
    0.08
    Activations Density 0.107%

    No Known Activations