© 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. 11493
    Prev
    Next
    INDEX
    Explanations

    International

    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
     Swinger
    -0.20
    ç»İ
    -0.19
    è¿ĩæĪ·
    -0.19
    æĿİåħĪçĶŁ
    -0.18
    ç»ı纪
    -0.18
     Geile
    -0.18
    evin
    -0.18
    ebin
    -0.17
    elier
    -0.17
    yz
    -0.17
    POSITIVE LOGITS
    æķ´ä¸ªäºº
    0.21
    .med
    0.20
    è¯ĺ
    0.18
    æ»ĵ
    0.18
    ç«¥
    0.18
     Japan
    0.18
    èĥŃ
    0.18
    รà¸ĵ
    0.18
     insign
    0.18
    .finish
    0.18
    Activations Density 0.004%

    No Known Activations