© 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. 31134
    Prev
    Next
    INDEX
    Explanations

    adoption, children, services

    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
    è¾ĩ
    -0.10
    å®īå®ģ
    -0.09
    åĪ«è¯´
    -0.08
    è°ª
    -0.08
    ä¸įç»ı
    -0.08
    åħļä¸Ń央
    -0.08
    ä¸įåIJĮäºİ
    -0.08
    GOP
    -0.08
    裸
    -0.08
     retreat
    -0.08
    POSITIVE LOGITS
    _mA
    0.10
    éĻ¢
    0.10
    çŃIJ
    0.10
    ëĦ
    0.10
     Krish
    0.09
    æĪijåıªæĺ¯
    0.09
    åѤåĦ¿
    0.09
    ç½®
    0.09
    èĤ¥
    0.09
     fatt
    0.09
    Activations Density 0.126%

    No Known Activations