© 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. 57924
    Prev
    Next
    INDEX
    Explanations

    police and military roles

    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
    çī¢
    -0.10
    essim
    -0.09
    nees
    -0.09
    è¶³å¤ŁçļĦ
    -0.09
    ufact
    -0.09
    俵
    -0.09
    ç»Ī究
    -0.09
    ifiers
    -0.09
    ÑģÑĤи
    -0.08
    足
    -0.08
    POSITIVE LOGITS
    egen
    0.09
    /xhtml
    0.09
    人æ°ijæľįåĬ¡
    0.08
    sar
    0.08
    æļ´
    0.08
    oping
    0.08
    积æŀģéħįåIJĪ
    0.08
    缴éĢļ车
    0.08
     situations
    0.08
    .invoke
    0.08
    Activations Density 0.122%

    No Known Activations