© 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. 62241
    Prev
    Next
    INDEX
    Explanations

    military and formal settings

    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
    icl
    -0.08
    æĦıæĦ¿
    -0.08
    æĬĹåĩ»
    -0.08
     dispro
    -0.08
     Sag
    -0.08
    agini
    -0.08
    å¥ij
    -0.08
    assed
    -0.08
    aign
    -0.08
    éĢĨè¡Į
    -0.08
    POSITIVE LOGITS
    纪å¾ĭ
    0.13
    ä¸¥æł¼çļĦ
    0.13
    éĽĨä½ĵ
    0.11
    ä¸¥æł¼
    0.11
    解æķ£
    0.11
    è¿Ŀ纪
    0.11
    åĵ¨
    0.10
    åĨĽå®ĺ
    0.10
     disciplinary
    0.10
    æķ´é¡¿
    0.10
    Activations Density 0.103%

    No Known Activations