© 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. 14346
    Prev
    Next
    INDEX
    Explanations

    calculator, calculating, calculations

    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¸Ģå±Ĥ
    -0.21
    structure
    -0.20
    nect
    -0.20
    åĽ¢
    -0.19
    .additional
    -0.19
    æķŀ
    -0.19
    æģº
    -0.19
     Alexandre
    -0.18
    onet
    -0.18
    Additional
    -0.18
    POSITIVE LOGITS
    计ç®ĹåĻ¨
    0.39
    计ç®Ĺ
    0.34
     calculator
    0.31
    å·¥åħ·
    0.28
     calculating
    0.27
    çļĦ帮åĬ©ä¸ĭ
    0.26
    çĶµéĩı
    0.25
     calculate
    0.25
     Calculator
    0.24
     Leather
    0.24
    Activations Density 0.076%

    No Known Activations