© 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. 20125
    Prev
    Next
    INDEX
    Explanations

    today and introductions

    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
    llen
    -0.10
    ï¸
    -0.09
    æĢ§å¼º
    -0.09
    é«ĺå°Ķ
    -0.09
    ate
    -0.09
    èļĤ
    -0.09
    ç»ĥ
    -0.08
    ä¾Ľè´§
    -0.08
     mate
    -0.08
    ä½ĵçİ°åľ¨
    -0.08
    POSITIVE LOGITS
    ä»Ĭ天æĪij们
    0.13
    ä»Ĭ天çļĦ
    0.13
    ä»Ĭ天
    0.12
     today
    0.11
     TODAY
    0.10
     Today
    0.10
    æĪij们è¦ģ
    0.09
    ä¸ĭéĿ¢æĪij们
    0.09
    bla
    0.08
    ä¸Ģä¼ļ
    0.08
    Activations Density 0.079%

    No Known Activations