© 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. 16179
    Prev
    Next
    INDEX
    Explanations

    classical works and plays

    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
    -BEGIN
    -0.22
    ĺ认
    -0.20
    åľ¨çݩ家ä¸Ń
    -0.19
    ifest
    -0.19
     Magnum
    -0.19
     prostitutes
    -0.18
    .promise
    -0.18
    malink
    -0.18
    åIJ¬è¯¾
    -0.18
    olvers
    -0.18
    POSITIVE LOGITS
    ç»ıåħ¸çļĦ
    0.32
    ç»ıåħ¸
    0.29
     classic
    0.27
     classics
    0.27
    æ¼Ķç»İ
    0.22
    è¯ŀ
    0.21
     Classics
    0.21
    åī§ç»Ħ
    0.21
    classic
    0.21
    ä¸Ģéĥ¨
    0.21
    Activations Density 0.021%

    No Known Activations