© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52468
    Prev
    Next
    INDEX
    Explanations

    crime and legal cases

    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
    é¦Ĵ头
    -0.11
    urs
    -0.10
    vw
    -0.08
    æĺ¨
    -0.08
    reso
    -0.08
    etur
    -0.08
    æĭ¥æĮ¤
    -0.08
    è¿İæĿ¥äºĨ
    -0.08
    ivity
    -0.08
     Holland
    -0.08
    POSITIVE LOGITS
    ä¹ŁæĽ¾
    0.12
    æĽ¾åľ¨
    0.12
    æľīä¸Ģ次
    0.11
    à¹Ģà¸Ħย
    0.11
    å¤ļ次
    0.11
    æĽ¾
    0.11
    ä»ĸæĽ¾
    0.11
    æĽ¾ç»ı
    0.10
     çeÅŁitli
    0.10
    æĹłæķ°æ¬¡
    0.10
    Activations Density 0.054%

    No Known Activations