© 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. 11132
    Prev
    Next
    INDEX
    Explanations

    and followed by a 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
    éĤ£æł·çļĦ
    -0.20
     "
    -0.19
    าย
    -0.18
    emet
    -0.18
     staples
    -0.18
     a
    -0.18
    APPER
    -0.18
    alom
    -0.17
    ate
    -0.17
     prime
    -0.17
    POSITIVE LOGITS
     Affero
    0.19
    建议
    0.19
    besch
    0.19
    建èŃ°
    0.19
    注æĦıäºĭ项
    0.19
    æ¿ij
    0.18
    æŃ£å½ĵ
    0.18
    ãĥªãĥ³ãĤ¯
    0.18
    æľīæķĪæĢ§
    0.18
     Pence
    0.17
    Activations Density 0.091%

    No Known Activations