© 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. 1433
    Prev
    Next
    INDEX
    Explanations

    features

    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
    å¿ĥä¸ŃçļĦ
    -0.10
    æĬµæĬĹåĬĽ
    -0.09
    czÄĻ
    -0.09
    å¿įåıĹ
    -0.08
    æľĢéķ¿
    -0.08
    èĮ¨
    -0.08
    å¿ĥä¸Ń
    -0.08
    æī¿åıĹ
    -0.08
     lore
    -0.08
    æľĢ好æĺ¯
    -0.08
    POSITIVE LOGITS
    诸å¦Ĥ
    0.10
    features
    0.10
     features
    0.09
    è´´å¿ĥ
    0.09
    .Singleton
    0.09
    ned
    0.09
    é½IJåħ¨
    0.08
    åĴĮå®ĮåĸĦ
    0.08
    _tim
    0.08
    ä¼ĺäºİ
    0.08
    Activations Density 0.133%

    No Known Activations