© 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. 15659
    Prev
    Next
    INDEX
    Explanations

    misdiagnoses, errors, mistakes

    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
    åıĹéĻIJ
    -0.21
    /helper
    -0.21
    RET
    -0.20
    ä¸ĢéĹª
    -0.20
    åı£æ°Ķ
    -0.20
    éļ¾åıĹ
    -0.20
    _demand
    -0.19
    Intent
    -0.19
     usu
    -0.19
    éĿ¢ä¸´çļĦ
    -0.19
    POSITIVE LOGITS
    失误
    0.35
    æ¼ı
    0.31
    éĶĻ误
    0.29
    éĶĻ
    0.28
     mish
    0.26
     оÑĪиб
    0.24
     mistakes
    0.24
    误
    0.24
     errors
    0.23
    æľįåĬ¡è´¨éĩı
    0.23
    Activations Density 0.236%

    No Known Activations