© 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. 14302
    Prev
    Next
    INDEX
    Explanations

    real-time information and analysis

    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
    /tests
    -0.19
    è¿©
    -0.19
    æĿĤçī©
    -0.19
    StringUtil
    -0.19
     Zuk
    -0.18
    èĤī
    -0.18
    éģİç¨ĭ
    -0.17
     procedure
    -0.17
    è·ŁçĿĢ
    -0.17
    à¹Ĥà¸Ł
    -0.17
    POSITIVE LOGITS
     updates
    0.24
     access
    0.21
    ouncer
    0.20
    身份
    0.19
    æĭ¥æľī
    0.19
    oref
    0.18
    毫ä¸į
    0.18
     ÑĢей
    0.18
    gre
    0.18
    æĽ´æĸ°
    0.18
    Activations Density 0.011%

    No Known Activations