© 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. 49032
    Prev
    Next
    INDEX
    Explanations

    health insurance industry

    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
    èį£
    -0.10
    åŀĽ
    -0.10
     Registr
    -0.09
    èį£èªī
    -0.09
    tdown
    -0.08
    ä¹IJåĽŃ
    -0.08
    KEN
    -0.08
    æĴķ
    -0.08
    itest
    -0.08
    榮
    -0.08
    POSITIVE LOGITS
    èĥĸåŃIJ
    0.11
    мол
    0.10
    æĬ¥éĶĢ
    0.10
    çĨ¨
    0.10
    åľ¨èģĮ
    0.10
    åĮ»èį¯
    0.09
    åĮ»ä¿Ŀ
    0.09
    å»ºåĽ½
    0.09
    绣çŃ¹
    0.09
    åıĤä¿Ŀ
    0.09
    Activations Density 0.257%

    No Known Activations