© 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. 14444
    Prev
    Next
    INDEX
    Explanations

    website URLs

    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
    深深çļĦ
    -0.21
    æ²¼
    -0.18
    åĿª
    -0.18
    å¸ľ
    -0.18
    æĤį
    -0.17
    vard
    -0.17
    aleb
    -0.17
    strup
    -0.17
    och
    -0.17
    uale
    -0.17
    POSITIVE LOGITS
    ä¸Ģé¡¿
    0.21
    ä¸İæѤ
    0.20
    贪婪
    0.19
    æīĵæĸŃ
    0.18
    èĥĥåı£
    0.18
    ä¸Ģ楼
    0.18
    urse
    0.18
    ä¸Ģæīĭ
    0.18
    åĴ¨è¯¢æľįåĬ¡
    0.17
    idot
    0.17
    Activations Density 0.043%

    No Known Activations