© 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. 34516
    Prev
    Next
    INDEX
    Explanations

    Los Angeles 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
    峤
    -0.10
    èķ²
    -0.10
    ä¼ģä¸ļæıIJä¾Ľ
    -0.09
    ä¸ĭä¸Ģ
    -0.09
     Хо
    -0.09
    _tm
    -0.08
    箬
    -0.08
    ä¸ĢæŶ
    -0.08
    addock
    -0.08
     дÑĥÑħ
    -0.08
    POSITIVE LOGITS
    æ´ĽæĿī磶
    0.12
    æµħ
    0.10
    éĴĹ
    0.09
    plen
    0.09
    woo
    0.09
    ressing
    0.09
    æĬĬæı¡
    0.09
    çĤİ
    0.09
     Los
    0.08
    opers
    0.08
    Activations Density 0.196%

    No Known Activations