© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8609
    Prev
    Next
    INDEX
    Explanations

    anomalous, glitch, exception

    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
    nown
    -0.12
     اÙĦتÙĤ
    -0.09
    Ùħات
    -0.09
    é«ĺæĸ°æĬĢæľ¯
    -0.09
    oric
    -0.08
    ä¸įåģļ
    -0.08
    éĺª
    -0.08
    è¿Ļä¹Īåģļ
    -0.08
    ç°ª
    -0.08
    _VISIBLE
    -0.08
    POSITIVE LOGITS
    åѤç«ĭ
    0.09
    amage
    0.08
    æĴĩ
    0.08
     Probe
    0.08
    çͳ
    0.08
    æİ¢
    0.08
    åºķéĥ¨
    0.08
     Latter
    0.08
    åѤ
    0.08
    æ¶İ
    0.08
    Activations Density 0.019%

    No Known Activations