© 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. 29739
    Prev
    Next
    INDEX
    Explanations

    older adults

    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
    ç²īä¸Ŀ
    -0.10
    аÑĢÑĮ
    -0.10
    èĤ¯å®ļä¼ļ
    -0.10
    é¢ĦåijĬ
    -0.09
    odb
    -0.09
    éĴ§
    -0.09
    çī¹èī²
    -0.09
    çĪ¸çĪ¸
    -0.09
    åİŁåĽłæĺ¯
    -0.09
    Anchor
    -0.09
    POSITIVE LOGITS
    èĢģ太太
    0.10
    èĢģ人
    0.10
    æĮĿ
    0.10
    èĢĦ
    0.09
    nap
    0.09
    åıŁ
    0.09
    ä¸įåłª
    0.09
    ÑĥÑĪки
    0.08
    alon
    0.08
    ä¸Ģ代
    0.08
    Activations Density 0.102%

    No Known Activations