© 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. 31175
    Prev
    Next
    INDEX
    Explanations

    Egypt and Egyptian topics

    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
    èĻļæŀĦ
    -0.10
     Pac
    -0.09
     Svens
    -0.08
    èģĶåIJĪ
    -0.08
    主ä¹īæĢĿæĥ³
    -0.08
    麾
    -0.08
    å®īå®ģ
    -0.08
    æĸ°çĸĨ
    -0.08
    çįIJ
    -0.08
    bp
    -0.08
    POSITIVE LOGITS
    åŁĥåıĬ
    0.21
     Egyptian
    0.18
    Egypt
    0.17
     Egypt
    0.17
    éĥijå·ŀ
    0.13
     Egyptians
    0.13
     Cairo
    0.12
     Nile
    0.12
    éĥijå·ŀå¸Ĥ
    0.12
    gypt
    0.11
    Activations Density 0.036%

    No Known Activations