© 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. 35928
    Prev
    Next
    INDEX
    Explanations

    Polish surnames and names

    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
    åĺ»
    -0.10
    lash
    -0.09
    裳
    -0.09
    logue
    -0.09
    PRI
    -0.09
    æĹħ游度åģĩ
    -0.09
    aries
    -0.08
    ierge
    -0.08
    ä¸ĢåĽ¢
    -0.08
    arith
    -0.08
    POSITIVE LOGITS
    abol
    0.09
    CHED
    0.09
    echa
    0.09
    egl
    0.08
    ÅĽÄĩ
    0.08
    czas
    0.08
    ä¸Ģéĥ¨åĪĨ
    0.08
    kowski
    0.08
    apon
    0.08
    cz
    0.08
    Activations Density 0.039%

    No Known Activations