© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52907
    Prev
    Next
    INDEX
    Explanations

    following "all"

    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
    æŀķ头
    -0.10
    è¿Ļä¹Ī说
    -0.10
    åĪ°æľĢåIJİ
    -0.10
    ä¹ĭ称
    -0.10
    æŶåĢĻ
    -0.10
    .byId
    -0.09
    äºĨæĪijçļĦ
    -0.09
    æĪ·åŀĭ
    -0.09
    éĻĩ
    -0.09
    æ°ijæĦı
    -0.09
    POSITIVE LOGITS
    iras
    0.08
    Workbook
    0.08
     ald
    0.08
    ä¸įæĸ¹ä¾¿
    0.08
    metis
    0.07
    oke
    0.07
    olib
    0.07
    elite
    0.07
    esk
    0.07
    indow
    0.07
    Activations Density 0.144%

    No Known Activations