© 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. 48977
    Prev
    Next
    INDEX
    Explanations

    category labels

    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
     (
    -0.08
     deb
    -0.08
    æıIJ
    -0.07
    è¿Ľé¡¹
    -0.07
    æľĹ
    -0.07
     ind
    -0.07
    åı°
    -0.07
     f
    -0.07
    表
    -0.07
    uro
    -0.07
    POSITIVE LOGITS
    责任ç¼ĸè¾ij
    0.12
    转载
    0.12
    ä»ħ代表
    0.10
    rette
    0.10
    æĸĩç«łæĿ¥æºIJ
    0.10
    ìĤ½
    0.10
    è´£ç¼ĸ
    0.10
    åŁŃ
    0.10
    abeth
    0.10
    ppe
    0.10
    Activations Density 0.037%

    No Known Activations