© 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. 29728
    Prev
    Next
    INDEX
    Explanations

    Okonomiyaki, Agave Master, chicken, Method, pyrethroids

    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
     Rugby
    -0.09
    æİīäºĨ
    -0.08
     IMO
    -0.08
    èį¤
    -0.08
    unde
    -0.08
    alten
    -0.08
    udes
    -0.08
    _nbr
    -0.08
    åIJĮäºĭ们
    -0.08
     Fat
    -0.08
    POSITIVE LOGITS
    TestClass
    0.10
    æĽĻ
    0.09
    lander
    0.09
    éĴ¢æĿ¿
    0.09
    æİĮ声
    0.09
    vana
    0.08
     ÑģебÑı
    0.08
    Ñģид
    0.08
    focus
    0.08
    çļij
    0.08
    Activations Density 0.009%

    No Known Activations