© 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. 33821
    Prev
    Next
    INDEX
    Explanations

    sports injuries

    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
    æľīåħ³è§Ħå®ļ
    -0.10
    ä¼łçľŁ
    -0.10
    anye
    -0.09
    ä¼ĺ
    -0.09
    çĸ¹
    -0.09
    éĴİ
    -0.09
    hausen
    -0.09
    æ´ij
    -0.08
    æıļ
    -0.08
     налиÑĩие
    -0.08
    POSITIVE LOGITS
    æIJ½
    0.10
    rag
    0.09
    elog
    0.09
    åĿIJä¸ĭ
    0.09
     оÑĤд
    0.08
    ä¸įæĺ¯å¾Ī
    0.08
    åģľçīĮ
    0.08
    åĬ¨æijĩ
    0.08
    æĨ§æĨ¬
    0.08
    åı¯æĺ¯
    0.08
    Activations Density 0.031%

    No Known Activations