© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20842
    Prev
    Next
    INDEX
    Explanations

    Santa Fe

    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
    èł¡
    -0.09
    çĻ½æ²Ļ
    -0.08
    妻
    -0.08
    ond
    -0.08
    èµĦæł¼
    -0.07
    HostName
    -0.07
    ä½Ĩä¸įéĻIJäºİ
    -0.07
     ‘
    -0.07
    æľīæĿĥ
    -0.07
    åªĴä½ĵæĬ¥éģĵ
    -0.07
    POSITIVE LOGITS
    plusplus
    0.10
    妹åŃIJ
    0.10
    赶快
    0.09
    ÙĬÙĪÙħ
    0.09
    eson
    0.09
    ä¸ĵ线
    0.09
    ãģªãģĦ
    0.09
    大家éĥ½åľ¨
    0.09
    kaar
    0.09
    å¼ĵ
    0.09
    Activations Density 0.003%

    No Known Activations