© 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. 54575
    Prev
    Next
    INDEX
    Explanations

    event handler listener

    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
    声èªī
    -0.09
    Credits
    -0.09
    åľ¨èģĮ
    -0.09
    以èī²
    -0.08
     Pron
    -0.08
    egie
    -0.08
    adar
    -0.08
     Libert
    -0.08
    spi
    -0.08
    æīī
    -0.08
    POSITIVE LOGITS
    æįķæįī
    0.11
    å¤ĦçIJĨ
    0.10
     handler
    0.10
     handlers
    0.10
    handler
    0.09
    (SIG
    0.09
    è¡İ
    0.09
     action
    0.09
    _HANDLER
    0.09
    .ActionEvent
    0.09
    Activations Density 0.419%

    No Known Activations