© 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. 40076
    Prev
    Next
    INDEX
    Explanations

    same or similar

    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
    åĽº
    -0.09
    ijo
    -0.09
    mars
    -0.09
     Spare
    -0.08
    ixa
    -0.08
    ãĤ·ãĥ¼
    -0.08
     Amar
    -0.08
    acle
    -0.08
     Fixture
    -0.08
    oha
    -0.08
    POSITIVE LOGITS
    缸åIJĮçļĦ
    0.33
    缸åIJĮ
    0.32
    åIJĮæł·çļĦ
    0.31
    ä¸Ģæł·çļĦ
    0.28
     same
    0.24
    åIJĮãģĺ
    0.23
    Same
    0.21
    same
    0.21
    åIJĮä¸Ģ个
    0.21
     similar
    0.21
    Activations Density 0.214%

    No Known Activations