© 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. 60962
    Prev
    Next
    INDEX
    Explanations

    Papua new guinea

    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
    ä»ĸçŁ¥éģĵ
    -0.09
     ÙĨÙĬ
    -0.09
    uels
    -0.08
    侧éĿ¢
    -0.08
    çķĶ
    -0.08
    çĶľçĶľ
    -0.08
    é©´
    -0.08
     Kick
    -0.08
    å¼ĢæĿ¥
    -0.08
     oci
    -0.08
    POSITIVE LOGITS
    åģļäºĭ
    0.09
    _CSR
    0.09
    ibir
    0.09
    _flight
    0.09
     Papua
    0.09
    è£ľ
    0.09
    .stamp
    0.09
     Tod
    0.09
    ä¿Ŀå¯Ĩ
    0.09
     Rub
    0.08
    Activations Density 0.067%

    No Known Activations