© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19536
    Prev
    Next
    INDEX
    Explanations

    programming code declarations

    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
    çIJĨäºĭéķ¿
    -0.09
    è¿Ļå¼ł
    -0.09
    ufe
    -0.09
    æŁ³
    -0.08
    ä¸įå°ij人
    -0.08
    ortal
    -0.08
     Pom
    -0.08
    Caption
    -0.08
    æ¯ķä¸ļ
    -0.08
    èIJ¥
    -0.08
    POSITIVE LOGITS
    auge
    0.09
    颧
    0.09
    åįµ
    0.09
    çļĦåĬªåĬĽ
    0.08
    è°Ģ
    0.08
     vard
    0.08
     clos
    0.08
    éķĢ
    0.08
    é²·
    0.08
    建åįİ
    0.08
    Activations Density 0.261%

    No Known Activations