© 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. 37510
    Prev
    Next
    INDEX
    Explanations

    maps and device locations

    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
    lay
    -0.10
    ä¸İä¼Ĺä¸įåIJĮ
    -0.09
    erea
    -0.09
    ç«¿
    -0.09
    illes
    -0.09
    ulp
    -0.09
    ilda
    -0.09
    æĮĪ
    -0.08
    ç´§å¯Ĩç»ĵåIJĪ
    -0.08
    红éħĴ
    -0.08
    POSITIVE LOGITS
    weg
    0.11
    ä¾µ
    0.09
    åºŁçī©
    0.09
    èIJ¥
    0.08
    CAF
    0.08
    omap
    0.08
    vir
    0.08
    æİ°
    0.08
     sed
    0.08
    æ±ł
    0.08
    Activations Density 0.175%

    No Known Activations