© 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. 49498
    Prev
    Next
    INDEX
    Explanations

    if you

    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
    Ñīа
    -0.09
    als
    -0.09
    ç¢
    -0.09
    顺çĿĢ
    -0.08
    IBLE
    -0.08
     ÑħоÑĢо
    -0.08
    getMock
    -0.08
    ALS
    -0.08
    强壮
    -0.08
    etting
    -0.08
    POSITIVE LOGITS
    æĪIJ份
    0.09
    åĽĽé¡¹
    0.09
    æĬķèµĦåŁºéĩij
    0.09
    åIJ¸çº³
    0.08
    该项
    0.08
    kl
    0.08
    æĬµæĮ¡
    0.08
    èĢģ大
    0.08
    åĽĽä¸ªæĸ¹éĿ¢
    0.08
    antis
    0.08
    Activations Density 0.030%

    No Known Activations