© 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. 31883
    Prev
    Next
    INDEX
    Explanations

    patriotism and country

    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
    å¤ĸæı´
    -0.09
    ings
    -0.09
    ond
    -0.09
    å¤ĸéĥ¨
    -0.09
     Universe
    -0.08
    ike
    -0.08
     organizers
    -0.08
    被迫
    -0.08
    sey
    -0.08
    åĨ¬å¥¥
    -0.08
    POSITIVE LOGITS
    åħ¼
    0.11
    çĩ®
    0.09
    .gc
    0.09
    .BatchNorm
    0.08
    ATAB
    0.08
    aren
    0.08
    表çĻ½
    0.08
    yard
    0.08
    ç¥Ģ
    0.08
    éĢĢå½¹
    0.08
    Activations Density 0.017%

    No Known Activations