© 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. 15655
    Prev
    Next
    INDEX
    Explanations

    phone numbers and codes

    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
    å®ŀè´¨
    -0.22
    继æī¿
    -0.21
    继ç»Ń
    -0.21
    wheel
    -0.19
    趣åij³
    -0.18
    æĥ¯ä¾ĭ
    -0.18
    éĻĦå±ŀ
    -0.18
     far
    -0.17
    /feed
    -0.17
    ãĥĴ
    -0.17
    POSITIVE LOGITS
    æ»´æ»´
    0.21
    éĵĽ
    0.19
    åIJĦæĸ¹éĿ¢
    0.19
     sag
    0.19
    acas
    0.19
    åİļåİļ
    0.18
    éľĩ
    0.17
    íĤ¹
    0.17
    ën
    0.17
    .Automation
    0.17
    Activations Density 0.076%

    No Known Activations