© 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. 34659
    Prev
    Next
    INDEX
    Explanations

    Names, often Asian, followed by hyphen or suffix

    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
    éħį
    -0.09
    åĪ°æĿ¥
    -0.09
    çľŁäºº
    -0.08
    ç«ĭå¿Ĺ
    -0.08
    scription
    -0.08
     Gund
    -0.08
    é£İåIJ¹
    -0.08
    mand
    -0.08
    éĿ
    -0.08
     Fer
    -0.07
    POSITIVE LOGITS
    æľ¬æľŁ
    0.10
    åĽº
    0.10
    ä½ľåĵģåĨħ容
    0.09
    æı®
    0.09
    åĩŃåĢŁ
    0.09
    ÅĹ
    0.09
     Stub
    0.09
     Epstein
    0.09
    ä¸ĢçĶŁ
    0.09
    åºĶ该å¦Ĥä½ķ
    0.08
    Activations Density 0.117%

    No Known Activations