© 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. 18320
    Prev
    Next
    INDEX
    Explanations

    told officials or groups

    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
    ãģªãģĹ
    -0.10
    欢è¿İæĤ¨
    -0.10
    åį´æ²¡æľī
    -0.09
    eric
    -0.09
    çļĦ身影
    -0.09
    äºĨ大éĩıçļĦ
    -0.09
    ç»Īæŀģ
    -0.09
    表éĿ¢ä¸Ĭ
    -0.09
    oui
    -0.09
    èĬĿ
    -0.09
    POSITIVE LOGITS
     rằng
    0.19
     bahwa
    0.15
     Ø£ÙĨ
    0.13
    ä»Ģä¹Īæĺ¯
    0.12
     że
    0.10
     how
    0.10
    åħ³äºİ
    0.10
     Ø£ÙĨÙĩ
    0.10
     hogy
    0.10
     بأÙĨ
    0.10
    Activations Density 0.095%

    No Known Activations