© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15722
    Prev
    Next
    INDEX
    Explanations

    numbers, counts, and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    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
    ImageContext
    -0.21
     wireType
    -0.21
    oland
    -0.21
    ERO
    -0.20
    å®īæİĴ
    -0.20
    neys
    -0.20
    ImplOptions
    -0.20
    åIJij社ä¼ļ
    -0.19
    æĹ¨åľ¨
    -0.19
    PropertyParams
    -0.19
    POSITIVE LOGITS
    åIJ¸å¼ķäºĨ
    0.23
    åIJ¸å¼ķ
    0.23
    åIJ¸å¼ķåĬĽ
    0.22
    åĽ´è§Ĥ
    0.22
    人æ°Ķ
    0.22
    èĿĮ
    0.21
    æĺŁæĺŁ
    0.21
     visitors
    0.21
    pop
    0.20
    Attr
    0.20
    Activations Density 0.042%

    No Known Activations