© 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. 11302
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives for people/populations

    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
    两边
    -0.09
    好å¤ļ
    -0.09
    èĬŃ
    -0.09
    gne
    -0.08
    ä¿Ŀåħ»
    -0.08
    å°ıå¾®
    -0.08
    æŁĶåĴĮ
    -0.08
    pute
    -0.08
    åĬĪ
    -0.08
    .jd
    -0.08
    POSITIVE LOGITS
     ones
    0.14
     themselves
    0.10
    ones
    0.10
     Ones
    0.09
     коÑĤоÑĢÑĭе
    0.09
     quienes
    0.09
    ä¹ĭ举
    0.08
    keiten
    0.08
    人士
    0.08
    æģ¨
    0.08
    Activations Density 0.066%

    No Known Activations