© 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. 27395
    Prev
    Next
    INDEX
    Explanations

    the structure of things

    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
    éĤ£ä¸Ģ
    -0.10
    使åħ¶
    -0.09
     themed
    -0.08
    ä¸Ģè´¯
    -0.08
    è¹ĩ
    -0.08
    nio
    -0.08
    伧
    -0.08
     serie
    -0.08
    erness
    -0.08
    icolor
    -0.08
    POSITIVE LOGITS
     Zimmerman
    0.10
    ä¸Ģæŀ¶
    0.09
    æıŃ
    0.08
    inals
    0.08
    presso
    0.08
    ç¿»
    0.08
    é¦ĸé¢Ĩ
    0.08
    å¤įèĭı
    0.08
    åĿŀ
    0.08
    à¹īà¸Ń
    0.08
    Activations Density 0.967%

    No Known Activations