© 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. 22732
    Prev
    Next
    INDEX
    Explanations

    discriminate or discriminate against

    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
    ettes
    -0.10
    ç»Ŀ
    -0.09
    æİ¢éĻ©
    -0.09
    à¸Ńม
    -0.09
    Mich
    -0.09
    åĨ³
    -0.09
    ç°ª
    -0.09
    顺德
    -0.08
    .microsoft
    -0.08
    NIC
    -0.08
    POSITIVE LOGITS
    ngen
    0.10
    å¼ĢæĿ¥
    0.09
    æĻĶ
    0.09
    ately
    0.09
    ä¹±
    0.09
    edium
    0.09
    æĸ¼æĺ¯
    0.09
    ially
    0.09
    éķ¿çŁŃ
    0.08
    ively
    0.08
    Activations Density 0.014%

    No Known Activations