© 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. 21846
    Prev
    Next
    INDEX
    Explanations

    wishing and welcoming

    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
    åºĦ
    -0.09
     sire
    -0.08
    fts
    -0.08
    æijĺ
    -0.08
    геÑĢ
    -0.08
    æĬĢæľ¯åĴĮ
    -0.08
     WithEvents
    -0.08
    æĭ¨
    -0.08
    åı¯ä¸įæĺ¯
    -0.08
    (TRUE
    -0.08
    POSITIVE LOGITS
    åģľçĶµ
    0.09
    åįĥä¸ĩåĪ«
    0.09
    æĬ»
    0.08
    ìĦ¤
    0.08
    åĽ´è§Ĥ
    0.08
    æĺ±
    0.08
    毡
    0.08
     winner
    0.08
    .Stretch
    0.08
    Delayed
    0.08
    Activations Density 0.030%

    No Known Activations