© 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. 35034
    Prev
    Next
    INDEX
    Explanations

    names starting with an or and

    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
    好人
    -0.09
    ụ
    -0.09
    chor
    -0.09
    /th
    -0.09
    æĥ³è¿ĩ
    -0.09
    NEL
    -0.08
    issor
    -0.08
    uyến
    -0.08
    åĩ«
    -0.08
    é«İ
    -0.08
    POSITIVE LOGITS
    ative
    0.09
    uce
    0.09
    éķ³
    0.09
    æŁĺ
    0.09
    æ¥
    0.08
    ä¼´
    0.08
    åŁŁ
    0.08
    满æĦı
    0.08
    èĬĭ
    0.08
     barn
    0.08
    Activations Density 0.005%

    No Known Activations