© 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. 6493
    Prev
    Next
    INDEX
    Explanations

    just wondering or curious

    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
    ãģĦãģı
    -0.09
    è¿«åĪĩ
    -0.09
    ç½Ħ
    -0.09
     dim
    -0.09
    ä¸įæĸŃåľ°
    -0.09
     То
    -0.08
    åIJ¸åħ¥
    -0.08
    eri
    -0.08
     Hem
    -0.08
    åĪ°åºķ
    -0.08
    POSITIVE LOGITS
    确认
    0.09
    _confirmation
    0.09
    æıIJéĨĴ
    0.08
    ä¼ĿãģĪ
    0.08
    å»ºåĽ½
    0.08
    åıįé¦Ī
    0.08
    ä¸Ģå°ı
    0.08
    å¥ī
    0.08
    _PKT
    0.08
    æ£Ģ
    0.08
    Activations Density 0.038%

    No Known Activations