© 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. 13937
    Prev
    Next
    INDEX
    Explanations

    Microsoft Office products

    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
    æľīæľŁ
    -0.20
    ackers
    -0.19
    rys
    -0.19
    GED
    -0.18
    acker
    -0.18
    ilee
    -0.18
    kke
    -0.17
    /values
    -0.17
    Rgb
    -0.17
    ufs
    -0.17
    POSITIVE LOGITS
    ç³»ç»Ł
    0.20
    ä¹ĭ家
    0.18
    ç³»ç»ŁçļĦ
    0.18
    人群ä¸Ń
    0.18
    ey
    0.17
    ç³»åĪĹ产åĵģ
    0.17
    ä¹ĭéģĵ
    0.17
    Subsystem
    0.17
    éĻĽ
    0.17
    åĨįåĬłä¸Ĭ
    0.17
    Activations Density 0.008%

    No Known Activations