© 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
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9343
    Prev
    Next
    INDEX
    Explanations

    accessing website in browser

    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
    ä¸Ĭåİ»
    -0.09
    ugen
    -0.09
    ä½ıäºĨ
    -0.09
    IDEOS
    -0.09
    æļ§
    -0.08
    éĺ»ç¢į
    -0.08
    åľ¨çº¿åĴ¨è¯¢
    -0.08
     daÃŁ
    -0.08
    _mono
    -0.08
    AZE
    -0.08
    POSITIVE LOGITS
     browsers
    0.10
    æĮĩå¼ķ
    0.09
    æīĵåį¡
    0.09
    缴æİ¥
    0.09
    miss
    0.09
     browser
    0.09
    ikel
    0.09
    _browser
    0.09
    .browser
    0.09
    eka
    0.09
    Activations Density 0.218%

    No Known Activations