© 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. 53672
    Prev
    Next
    INDEX
    Explanations

    genetic variation, former species

    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
    æ½
    -0.11
    è¦Ĩ
    -0.10
    ä¸Ģ次æĢ§
    -0.10
    ä¹Łæĺ¯å¾Ī
    -0.10
    ä¸Ģ次
    -0.09
    涨
    -0.09
    æĺ¼
    -0.09
    tere
    -0.09
    unders
    -0.09
    山路
    -0.09
    POSITIVE LOGITS
    人为
    0.11
    èĩªä¸»åĵģçīĮ
    0.10
     ÙħØŃÙħ
    0.09
    åĩłå¼ł
    0.09
    inke
    0.09
    诱
    0.09
    EOS
    0.09
     Ballet
    0.08
    ç»Ī身
    0.08
    天çĶŁ
    0.08
    Activations Density 0.055%

    No Known Activations