© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5981
    Prev
    Next
    INDEX
    Explanations

    Myanmar and Burma

    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
    æĺİæĻ°
    -0.09
    èĢĺ
    -0.09
    _MODAL
    -0.08
    око
    -0.08
    mos
    -0.08
    管è¾ĸ
    -0.08
    nuts
    -0.08
    hips
    -0.08
    itor
    -0.08
    _modal
    -0.08
    POSITIVE LOGITS
    icum
    0.10
    æĮĿ
    0.10
    ormal
    0.10
    åĽĽé¡¹
    0.09
    Ùģار
    0.09
    _pri
    0.09
    æĤ£
    0.09
    åºĬä½į
    0.09
    æģ¨ä¸įå¾Ĺ
    0.09
    arden
    0.09
    Activations Density 0.015%

    No Known Activations