© 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. 16818
    Prev
    Next
    INDEX
    Explanations

    changes or updates

    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
     Wish
    -0.21
    ä¸Ģç«Ļ
    -0.21
     Entered
    -0.19
    ä½ľåĿĬ
    -0.19
    .hm
    -0.19
    ç½ijç»ľä¼łæĴŃ
    -0.19
    offsetof
    -0.19
    ahir
    -0.18
    åĿĿ
    -0.18
    èµİ
    -0.18
    POSITIVE LOGITS
     unread
    0.25
    unread
    0.23
    æĮĩ示
    0.21
    Alert
    0.21
    æľīèī²
    0.20
    sted
    0.19
    .changed
    0.19
    .plist
    0.19
    Indicator
    0.19
     alert
    0.19
    Activations Density 0.076%

    No Known Activations