© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33756
    Prev
    Next
    INDEX
    Explanations

    women's issues

    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
    bern
    -0.10
    让ä»ĸ们
    -0.10
    è¦ĨçĽĸéĿ¢
    -0.09
    PackageManager
    -0.09
    ä¸į大
    -0.09
     кÑĢÑĥ
    -0.09
     Rouge
    -0.09
     dép
    -0.09
    bow
    -0.09
    .gf
    -0.09
    POSITIVE LOGITS
    çĶŁäº§åĴĮ
    0.09
     barred
    0.08
    ä¸įåģľçļĦ
    0.08
    丰å¯Įå¤ļ彩
    0.08
     Woodward
    0.08
    odi
    0.08
    éĢĴ
    0.08
    æijĪ
    0.08
    æģķ
    0.08
     idi
    0.08
    Activations Density 0.067%

    No Known Activations