© 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. 4195
    Prev
    Next
    INDEX
    Explanations

    delinquent, default, overdue

    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
     cov
    -0.10
    é¾Ł
    -0.08
    ä¸įæĪIJ
    -0.08
    orm
    -0.08
    æ²ģ
    -0.08
    æ³ķ令
    -0.08
    æĹłç©·
    -0.08
    èĮĥåĽ´åĨħ
    -0.08
    å¡Į
    -0.08
     Vest
    -0.08
    POSITIVE LOGITS
    ìĤ¬íķŃ
    0.10
    ennis
    0.10
    ingleton
    0.09
    çİĩ
    0.09
    å§ĭäºİ
    0.09
     tú
    0.09
    éĢĥéģ¿
    0.09
    累累
    0.09
    æ¸Į
    0.09
    cies
    0.08
    Activations Density 0.013%

    No Known Activations