© 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. 35251
    Prev
    Next
    INDEX
    Explanations

    convert energy or signals

    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
    ÑģпоÑģоб
    -0.11
    被èªī为
    -0.09
     ÑĤеле
    -0.09
    æĪ´
    -0.09
     eco
    -0.09
     cara
    -0.09
    panion
    -0.08
    IRO
    -0.08
    ÑģÑĤÑĢа
    -0.08
     Hamp
    -0.08
    POSITIVE LOGITS
    转åĮĸ为
    0.19
    转åĮĸ
    0.17
    转åıĺ为
    0.15
    转æį¢
    0.14
     converting
    0.13
    èµĦæºIJä¼ĺåĬ¿
    0.13
    æĪIJæŀľè½¬åĮĸ
    0.12
     Convert
    0.12
    ç§ijæĬĢæĪIJæŀľ
    0.12
     convert
    0.12
    Activations Density 0.136%

    No Known Activations