© 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. 23371
    Prev
    Next
    INDEX
    Explanations

    programming concepts (interface, class, method)

    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
    ç»ıå¼Ģ
    -0.08
    磻
    -0.08
    boro
    -0.08
    åıĸå¾Ĺ
    -0.08
    èĭŁ
    -0.08
    åIJĦçľģ
    -0.07
    ç»ı纬
    -0.07
    uco
    -0.07
    bsp
    -0.07
     adm
    -0.07
    POSITIVE LOGITS
    æļ®
    0.09
    _slots
    0.09
    UNCTION
    0.09
    ä¸Ģå¹ķ
    0.09
    å®ļä¹ī
    0.09
     flesh
    0.09
    declaring
    0.09
    åħ¬å¼Ģåıij
    0.09
    .createClass
    0.08
    class
    0.08
    Activations Density 1.965%

    No Known Activations