© 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. 22762
    Prev
    Next
    INDEX
    Explanations

    growing population demands

    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
    æĬ¥ç¤¾
    -0.09
    å¹ķ
    -0.09
    arel
    -0.09
    åĨ·éĵ¾çī©æµģ
    -0.09
    æĹłåģ¿
    -0.09
    åĩĢåĢ¼
    -0.09
    .ActionListener
    -0.09
    è¯ķè¡Į
    -0.09
    åľ¨çİ°åľº
    -0.09
    åĨ°éĽª
    -0.09
    POSITIVE LOGITS
    æī©å®¹
    0.19
    å¢ŀéķ¿
    0.16
     growth
    0.15
    容éĩı
    0.15
    æī©å¼ł
    0.15
    çļĦå¢ŀéķ¿
    0.14
    å¿«éĢŁå¢ŀéķ¿
    0.14
    容纳
    0.13
     capacity
    0.13
    capacity
    0.13
    Activations Density 0.098%

    No Known Activations