© 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. 12729
    Prev
    Next
    INDEX
    Explanations

    : looking for lists or tables

    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
    åij½è¿IJ
    -0.21
    à¸Ĥà¸Ļา
    -0.20
    æ»ļ
    -0.20
    ipple
    -0.19
    inery
    -0.19
    èĮĮ
    -0.18
    ä¸įåı¯èĥ½
    -0.18
    ANNEL
    -0.18
    è¿ĺæľī
    -0.18
    ureau
    -0.18
    POSITIVE LOGITS
    ä¸Ģ个æĺ¯
    0.32
    ä¸Ģæĺ¯
    0.30
    é¦ĸåħĪæĺ¯
    0.25
    åĪĨåĪ«æĺ¯
    0.25
    æĪijåĴĮ
    0.24
    ç»ıéªĮåĴĮ
    0.23
    ä¼ģä¸ļåĴĮ
    0.23
    èĥ½åĬĽåĴĮ
    0.22
    建设åĴĮ
    0.20
    åħĪæĺ¯
    0.20
    Activations Density 0.145%

    No Known Activations