© 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. 10836
    Prev
    Next
    INDEX
    Explanations

    business entities and affiliations

    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
    家éķ¿ä»¬
    -0.09
    ese
    -0.08
    imat
    -0.08
    éªij
    -0.08
    cki
    -0.08
    裸
    -0.08
    iten
    -0.07
    çļĦåIJĦç§į
    -0.07
    .inst
    -0.07
    ocked
    -0.07
    POSITIVE LOGITS
    仲
    0.09
     Roose
    0.09
    ä¸įä¹ħ
    0.09
    eut
    0.09
    ä¸įç»ı
    0.09
    åıĮåıĮ
    0.09
    åį§
    0.09
    ç´łè´¨
    0.09
    é¢Ŀ头
    0.09
    丧
    0.08
    Activations Density 0.043%

    No Known Activations