© 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. 50078
    Prev
    Next
    INDEX
    Explanations

    language codes and names

    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
    çļĦéģĵè·¯
    -0.09
    vero
    -0.09
    زÙħ
    -0.09
    تب
    -0.08
    çĻ¾ç§ij
    -0.08
     McB
    -0.08
    çijĻ
    -0.08
    åĮ¹
    -0.08
    é¦Ĩ
    -0.08
    lier
    -0.08
    POSITIVE LOGITS
    ä¸Ńæĸĩ
    0.17
     English
    0.15
    èĭ±è¯Ń
    0.15
    æ±ī
    0.14
    æ±īè¯Ń
    0.14
    èĭ±æĸĩ
    0.14
    English
    0.14
    english
    0.13
     англий
    0.12
     Arabic
    0.12
    Activations Density 0.162%

    No Known Activations