© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12319
    Prev
    Next
    INDEX
    Explanations

    sharing resources between entities

    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
    æĸ°çļĦ
    -0.20
    æģ°
    -0.19
    人群ä¸Ń
    -0.18
    失
    -0.18
    inaire
    -0.17
    atically
    -0.17
    edral
    -0.17
    å®ŀäºĭ
    -0.17
    endant
    -0.17
    å¼¼
    -0.17
    POSITIVE LOGITS
    /shared
    0.21
     responsibility
    0.21
     between
    0.20
    çĿĢ
    0.19
     responsibilities
    0.19
     междÑĥ
    0.19
    /Common
    0.19
     giữa
    0.18
    /common
    0.18
    åij¼åIJ¸
    0.18
    Activations Density 0.041%

    No Known Activations