© 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. 34902
    Prev
    Next
    INDEX
    Explanations

    plural and singular forms

    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
    ä¸Ĭä¸ĭ
    -0.10
    龸éģĵ
    -0.09
     Wings
    -0.08
    ä¿Ŀå§Ĩ
    -0.08
    5
    -0.08
     reli
    -0.08
    4
    -0.08
    8
    -0.08
    6
    -0.08
    èĪħèĪħ
    -0.08
    POSITIVE LOGITS
    åĿļ
    0.10
    æĪĪ
    0.09
    æ²±
    0.09
    饩
    0.09
    .future
    0.09
    æĿŀ
    0.09
    ä¸ĭä¸Ģ
    0.09
    kest
    0.08
    abo
    0.08
    å¡«æĬ¥
    0.08
    Activations Density 0.059%

    No Known Activations