© 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. 19031
    Prev
    Next
    INDEX
    Explanations

    water-resistant coating

    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
    iani
    -0.09
    èĪ«
    -0.09
    çĻ½éĽª
    -0.09
    æĭĹ
    -0.09
    otron
    -0.09
    ä¼Łå¤§çļĦ
    -0.08
    crest
    -0.08
    xFFFFFFFF
    -0.08
    åĿ·
    -0.08
     Dirt
    -0.08
    POSITIVE LOGITS
    ç¨ĭ度
    0.11
    ï¸ı
    0.09
    ä½ıäºĨ
    0.08
    æĢ§åĴĮ
    0.08
     bogus
    0.08
    ably
    0.08
    .func
    0.08
    çļĦç¨ĭ度
    0.08
    ä¸Ĭä¸ĭ
    0.08
    æİ¥åIJ¬
    0.08
    Activations Density 0.033%

    No Known Activations