© 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. 4464
    Prev
    Next
    INDEX
    Explanations

    towns and celebrities

    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
    妻åŃIJ
    -0.11
     wife
    -0.09
    çļĦ妻åŃIJ
    -0.09
    é³ı
    -0.09
    夫人
    -0.09
    èĨĽ
    -0.09
    妻
    -0.08
    çĭ±
    -0.08
    太太
    -0.08
    常
    -0.08
    POSITIVE LOGITS
    å°ij女
    0.13
    éĿĴæĺ¥æľŁ
    0.12
    女åŃ©
    0.12
    女åŃ©åŃIJ
    0.12
     дев
    0.11
    代è¨Ģ
    0.11
    女çĶŁ
    0.10
     girls
    0.10
     teens
    0.10
     girl
    0.10
    Activations Density 0.088%

    No Known Activations