© 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. 14665
    Prev
    Next
    INDEX
    Explanations

    work in progress, TODO, FIXME, missing

    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
    ä»İä¸ļèĢħ
    -0.19
    æĭ¥æĬ¤
    -0.19
     capt
    -0.19
    âľķ
    -0.19
    ä¹Łä¸įæķ¢
    -0.18
    hip
    -0.18
    ç¥İ
    -0.18
    çĶ¬
    -0.18
    ifu
    -0.18
     Land
    -0.17
    POSITIVE LOGITS
    对æĪijæĿ¥è¯´
    0.21
    èģĶ
    0.19
    ä¸ĬæĿ¥
    0.19
    建设工ç¨ĭ
    0.19
    解
    0.18
    èģ¯
    0.17
    à¸Ĥาà¸Ķ
    0.17
    etch
    0.17
    ä¸Ĭåīį
    0.17
    èŀ½
    0.17
    Activations Density 0.002%

    No Known Activations