© 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. 15461
    Prev
    Next
    INDEX
    Explanations

    downloading files

    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
    Singleton
    -0.23
    åģ¶å°Ķ
    -0.21
    unner
    -0.21
    opsis
    -0.20
    atable
    -0.20
    åĮĹæĸĹ
    -0.20
    FilterWhere
    -0.19
     pad
    -0.19
    alus
    -0.19
     dispens
    -0.19
    POSITIVE LOGITS
     ÑĦайл
    0.24
    downloads
    0.22
    ä¸ĭè½½
    0.22
     ÑĦайла
    0.21
    æĸĩ件
    0.21
    èħ¾é£ŀ
    0.20
     olarak
    0.20
    ãĥĪãĤ¤
    0.19
    æīĭå¥Ĺ
    0.19
    (Resources
    0.19
    Activations Density 0.043%

    No Known Activations