© 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. 27897
    Prev
    Next
    INDEX
    Explanations

    duration or extent

    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
    æĽ´å¤ļä¿¡æģ¯
    -0.10
    å»Ĭ
    -0.10
    ordo
    -0.09
     convers
    -0.09
    ridge
    -0.09
    coop
    -0.09
    æľ¬ç½ijç«Ļ
    -0.08
    EAR
    -0.08
    çİĭèĢħ
    -0.08
    ä»İå°ıå°±
    -0.08
    POSITIVE LOGITS
     lasted
    0.10
    大èĩ´
    0.10
    缴åĪ°
    0.09
    ÑĤал
    0.09
    缴èĩ³
    0.09
    à¸ģระà¸Ĺ
    0.09
    åĽ¢
    0.09
     Duration
    0.08
    ä¸Ģ缴åĪ°
    0.08
    åĪ°æľĢåIJİ
    0.08
    Activations Density 0.092%

    No Known Activations