© 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. 11166
    Prev
    Next
    INDEX
    Explanations

    nutrients and supplements

    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
    bling
    -0.21
    è¿Ļ个èģĮä¸ļ
    -0.21
    æĭĴ
    -0.21
    æıŃ示
    -0.20
    天æīį
    -0.20
    å¹ķ
    -0.20
    vé
    -0.19
    tern
    -0.19
    ç£ħ
    -0.18
    AtA
    -0.18
    POSITIVE LOGITS
    éĢĤéĩı
    0.20
    æ»ĭ润
    0.19
    åij¼å£°
    0.19
    æµ·å²Ľ
    0.19
     errorHandler
    0.19
    ãģłãģijãģ§
    0.19
    иÑĢованиÑı
    0.18
     moduleId
    0.18
    erva
    0.18
    磫æŃ£
    0.18
    Activations Density 0.023%

    No Known Activations