© 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. 13590
    Prev
    Next
    INDEX
    Explanations

    drinking water

    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
     Boyd
    -0.22
    å¾Ĺ以
    -0.20
    çĸij
    -0.19
     BP
    -0.19
    BP
    -0.18
    eld
    -0.18
     Meet
    -0.18
    就被
    -0.17
    zers
    -0.17
     Bran
    -0.17
    POSITIVE LOGITS
    ãģ¨ãĤĤ
    0.23
    ulary
    0.21
    çļĦæĦıæĢĿ
    0.20
    -upper
    0.19
    волÑĮ
    0.19
    Whatever
    0.19
    .strings
    0.18
    ä¸ĢåĽŀäºĭ
    0.18
    éºŁ
    0.18
     whichever
    0.18
    Activations Density 0.214%

    No Known Activations