© 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. 11311
    Prev
    Next
    INDEX
    Explanations

    possessive or connector followed by noun

    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
    æĪIJ为ä¸ĢåIJį
    -0.24
    æĺ¯ä¸ĢåIJį
    -0.23
    ä½ľä¸ºä¸ĢåIJį
    -0.22
    çļĦ妻åŃIJ
    -0.21
    hasOne
    -0.20
     пÑĥÑĤеÑĪеÑģÑĤв
    -0.20
    æĪijå¦Ī
    -0.20
    å¿įä¸įä½ı
    -0.19
    Ñģ
    -0.19
    æĺ¯ä¸Ģä½į
    -0.19
    POSITIVE LOGITS
    é¢Ĩè¢ĸ
    0.23
    é¢Ĩ导人
    0.23
    è¯īæ±Ĥ
    0.22
     Tactics
    0.22
     leader
    0.22
    æĪIJåijĺ
    0.21
    ischer
    0.21
     itself
    0.21
    é¦ĸé¢Ĩ
    0.21
    arcer
    0.20
    Activations Density 0.053%

    No Known Activations