© 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. 18962
    Prev
    Next
    INDEX
    Explanations

    sweetness

    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
    åĨ°åĨ·
    -0.09
    æĸ°å¢ŀ
    -0.09
    vale
    -0.08
    èĦ¸
    -0.08
    nika
    -0.08
    holm
    -0.08
    oj
    -0.08
    ÑĢен
    -0.08
    tower
    -0.08
    æłĩæĺİ
    -0.08
    POSITIVE LOGITS
    度
    0.11
    CHED
    0.09
    à¹ĩà¸Ķ
    0.09
    åķ¸
    0.08
    axis
    0.08
    éªij
    0.08
     Gem
    0.08
     inde
    0.08
    稳
    0.08
    ete
    0.08
    Activations Density 0.003%

    No Known Activations