© 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. 10937
    Prev
    Next
    INDEX
    Explanations

    1 min read

    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
    æĬ±çĿĢ
    -0.22
    大åŀĭ
    -0.20
    abama
    -0.19
    å¸IJ篷
    -0.19
    ullo
    -0.19
     Riy
    -0.18
    é¹ľ
    -0.18
    éĢĴ
    -0.17
    纡
    -0.17
     ÑĢазвиÑĤ
    -0.17
    POSITIVE LOGITS
    å¾Īç®Ģåįķ
    0.24
    ç®Ģ便
    0.21
    asher
    0.21
    ç®Ģåįķ
    0.21
     dÃ¼ÅŁ
    0.21
     simple
    0.20
    upo
    0.20
    æį·
    0.20
     simplest
    0.19
    ç®ĢåįķçļĦ
    0.19
    Activations Density 0.192%

    No Known Activations