© 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. 12119
    Prev
    Next
    INDEX
    Explanations

    aerospace industry professionals

    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
    ss
    -0.09
    aket
    -0.09
    chia
    -0.09
    ordon
    -0.08
    erate
    -0.08
    usc
    -0.08
    rok
    -0.08
    è¿Ļ个æŶåĢĻ
    -0.08
    ry
    -0.08
    èĬĹ
    -0.08
    POSITIVE LOGITS
    人士
    0.10
    é¹ķ
    0.10
    æĽĻ
    0.10
    ẳng
    0.09
     ÑģебÑı
    0.09
     Allan
    0.09
    quential
    0.09
    ວ
    0.09
    -grade
    0.09
    大äºĭ
    0.09
    Activations Density 0.019%

    No Known Activations