© 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. 53892
    Prev
    Next
    INDEX
    Explanations

    forms of 'to be' followed by a descriptor

    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
    /container
    -0.10
     Lay
    -0.10
    /forum
    -0.09
    åIJĦèĩª
    -0.09
    Poss
    -0.09
     بÙĬ
    -0.09
    lay
    -0.09
    æĥĭ
    -0.09
    /API
    -0.08
    æ§
    -0.08
    POSITIVE LOGITS
    æĺ¯ä¸Ģ项
    0.13
    çļĦä¸Ģ项
    0.12
    ä¸Ģ项
    0.12
    æĺ¯ä¸Ģ件
    0.11
    ä½ľä¸ºä¸Ģç§į
    0.10
    è¿Ļ项
    0.10
    ä¸Ģ件
    0.10
    è¿Ļ个èģĮä¸ļ
    0.10
    ä¸Ģ个èģĮä¸ļ
    0.10
    头æĿ¡
    0.10
    Activations Density 0.206%

    No Known Activations