© 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. 12921
    Prev
    Next
    INDEX
    Explanations

    what they mean by

    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
    ä½ľèĢħæľ¬äºº
    -0.21
    ä½ļ
    -0.21
    èµ·çłģ
    -0.20
    ÙĪجÙĩ
    -0.19
     Hoy
    -0.18
    å°±æľī
    -0.18
    аÑĢа
    -0.18
    彬
    -0.18
    æīĢèĥ½
    -0.18
    éĿ¢åīį
    -0.17
    POSITIVE LOGITS
     referring
    0.23
    _MT
    0.21
    å¹²éĥ¨
    0.20
     vague
    0.20
    anguage
    0.20
     unc
    0.19
     refers
    0.19
    æĦıæĢĿ
    0.19
    azy
    0.18
    æĮĩçļĦæĺ¯
    0.18
    Activations Density 0.042%

    No Known Activations