© 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. 16672
    Prev
    Next
    INDEX
    Explanations

    sung lyrics and vocals

    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
    erv
    -0.27
    ä¸ĢæĹ¥
    -0.20
    ylie
    -0.20
    åĽ¤
    -0.20
    .books
    -0.19
     Brill
    -0.19
    insula
    -0.19
    eus
    -0.19
    ä¸Ģ天
    -0.18
    éĦ¢
    -0.18
    POSITIVE LOGITS
    è¿Ļé¦ĸæŃĮ
    0.32
    è¿Ļé¦ĸ
    0.30
    èĬĤå¥ı
    0.28
    æŃĮè¯į
    0.27
    æŃĮæĽ²
    0.26
     sung
    0.24
     singer
    0.24
     vocals
    0.24
    æŃĮåĶ±
    0.23
    广大群ä¼Ĺ
    0.23
    Activations Density 0.031%

    No Known Activations