© 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. 16052
    Prev
    Next
    INDEX
    Explanations

    cataract extraction, lens opacity

    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
    çķİ
    -0.20
    ä¸įä¿¡
    -0.20
    æľĭåıĭ们
    -0.20
    é£İåIJ¹
    -0.19
    jen
    -0.19
    éĨĴ缮
    -0.19
    éĹ¾
    -0.19
    æ©Ľ
    -0.19
    vertis
    -0.19
    çªĴæģ¯
    -0.18
    POSITIVE LOGITS
     полно
    0.23
    odia
    0.21
    ç¢İçīĩ
    0.20
    èĬĿ麻
    0.20
     ÑįкÑģ
    0.20
     Voc
    0.19
     granny
    0.19
    糯
    0.19
    AGING
    0.18
    _lens
    0.18
    Activations Density 0.065%

    No Known Activations