© 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. 49641
    Prev
    Next
    INDEX
    Explanations

    numbers and specific terms

    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
    ç«ŀæĬĢ
    -0.08
    ä¸ĭåİ»
    -0.08
     ÑĦигÑĥÑĢ
    -0.08
    èŁ¾
    -0.08
    贵宾
    -0.08
    Ñģад
    -0.08
    å¾ĹäºĨ
    -0.08
    好äºĨ
    -0.08
    泫
    -0.08
    ·»
    -0.08
    POSITIVE LOGITS
    TemplateName
    0.09
    仪
    0.09
    éĢ¸
    0.09
    avo
    0.09
    æī«ä¸Ģæī«
    0.08
    èµĦæºIJä¼ĺåĬ¿
    0.08
    æ¯Ķè¾ĥé«ĺ
    0.08
     trÆ°á»Łng
    0.08
    缺å¸Ń
    0.08
    è¿Ľå±ķæĥħåĨµ
    0.08
    Activations Density 0.007%

    No Known Activations