© 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. 31219
    Prev
    Next
    INDEX
    Explanations

    names of wives or noblewomen

    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
     девÑĥÑĪ
    -0.09
    å°ı女åŃ©
    -0.09
    OCK
    -0.09
    locker
    -0.09
    ock
    -0.08
    çļĦ女åŃ©
    -0.08
    女åŃ©åŃIJ
    -0.08
    毫
    -0.08
    综åIJĪæ²»çIJĨ
    -0.08
    å°ıå§ijå¨ĺ
    -0.08
    POSITIVE LOGITS
    夫人
    0.14
    天é¹ħ
    0.10
    oil
    0.09
    夫
    0.09
    çļĦåľ°ä½į
    0.09
    accordion
    0.09
     --------------------------------------------------------------------------↵
    0.09
    å¿į
    0.09
    nest
    0.09
    æ²īæµ¸åľ¨
    0.09
    Activations Density 0.086%

    No Known Activations