© 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. 12141
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or abbreviations

    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
    ores
    -0.10
    èķ¤
    -0.10
    人éĥ½
    -0.09
    issen
    -0.09
    sic
    -0.09
     Boston
    -0.09
    itim
    -0.08
    itical
    -0.08
    ney
    -0.08
    isch
    -0.08
    POSITIVE LOGITS
    utes
    0.10
    รวà¸Ķ
    0.09
    æ§
    0.09
    OrCreate
    0.08
     GLFW
    0.08
    biz
    0.08
    ways
    0.08
    éĹ¼
    0.08
    ario
    0.08
    ä¸įæİĴéĻ¤
    0.08
    Activations Density 0.297%

    No Known Activations