© 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. 50923
    Prev
    Next
    INDEX
    Explanations

    non-European countries

    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
    åį³ä½¿
    -0.09
    ople
    -0.09
    çĭ®
    -0.08
    æŃ£åĽłä¸º
    -0.08
    à¸Ńà¸ĩ
    -0.08
     FT
    -0.08
    èĨĿ
    -0.08
    atak
    -0.08
    uft
    -0.07
    ope
    -0.07
    POSITIVE LOGITS
    èĢĮæĺ¯
    0.12
    azor
    0.11
    以å¤ĸ
    0.10
    ä¹ĭå¤ĸ
    0.10
    æľ¬èº«çļĦ
    0.10
    ìłľ
    0.09
    éĩįå·¥
    0.09
    .tem
    0.09
    æ±²åıĸ
    0.09
     Estates
    0.09
    Activations Density 0.183%

    No Known Activations