© 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. 29482
    Prev
    Next
    INDEX
    Explanations

    schools and education

    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
    Negative Logits
    åĥ§
    -0.11
    å®ī康
    -0.10
    à¸Ńà¸Ń
    -0.09
    aph
    -0.08
    交æµģåIJĪä½ľ
    -0.08
    หลวà¸ĩ
    -0.08
    æĴ¸
    -0.08
    TABLE
    -0.08
    ÙĨع
    -0.08
    .delegate
    -0.08
    POSITIVE LOGITS
    åĮħ容
    0.09
    åijĪ
    0.09
     spine
    0.08
    åħ¸
    0.08
    kart
    0.08
    пÑĢод
    0.08
    è¿ľæĻ¯
    0.08
    PTS
    0.08
    pts
    0.08
    ALSE
    0.08
    Activations Density 0.063%

    No Known Activations