© 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. 33820
    Prev
    Next
    INDEX
    Explanations

    attend / attending / attendance

    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
    çĭ·
    -0.08
    åŃĶéĽĢ
    -0.08
    bach
    -0.08
    ãģ»
    -0.08
     sürekli
    -0.08
     Fridays
    -0.08
    å¥ij
    -0.08
     überh
    -0.08
    ãĥĬãĥ«
    -0.08
    ä¸įåıĺ
    -0.08
    POSITIVE LOGITS
    åīįä¸ĸ
    0.10
    æľªç»ıæİĪæĿĥ
    0.10
    è¿Ļåľº
    0.10
    æѦè£ħ
    0.09
    ANA
    0.09
    å¸Ĥä¸Ńå¿ĥ
    0.09
    adel
    0.09
    é¦ĸè½®
    0.08
     Hubb
    0.08
    çļĦæĦ¿æľĽ
    0.08
    Activations Density 0.035%

    No Known Activations