© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21381
    Prev
    Next
    INDEX
    Explanations

    names like Marco, Mario, Andrew, Marc

    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
    ä½Ĩæĺ¯ä»ĸ
    -0.09
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.09
    娱
    -0.09
    æĸĽ
    -0.09
    å°ijçĪ·
    -0.09
    .ms
    -0.09
    å½Ŀ
    -0.09
    迹
    -0.09
    ä¸ĸçķĮä¸ĬæľĢ
    -0.08
    ãĤĤãģ¡ãĤįãĤĵ
    -0.08
    POSITIVE LOGITS
    ubs
    0.09
    æľīä»Ģä¹Ī
    0.08
    _fa
    0.08
    éħįåIJĪ
    0.08
    æľŁå¾ħ
    0.08
     Propel
    0.08
     Fletcher
    0.08
    æľīä½ķ
    0.08
    UDA
    0.08
    æĸ°çļĦä¸Ģ
    0.08
    Activations Density 0.119%

    No Known Activations