© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12590
    Prev
    Next
    INDEX
    Explanations

    Race, Kart, Piece, line

    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
    ä¾
    -0.20
    æģ
    -0.20
    æīĭæĮĩ
    -0.19
    æħij
    -0.19
    æݨèĸ¦
    -0.19
    isions
    -0.19
    èѦåĬ¡
    -0.19
    ridged
    -0.19
    æݨèįIJ
    -0.19
    çħ¤çŁ¿
    -0.18
    POSITIVE LOGITS
    .travel
    0.21
    æĹħè¡Į
    0.20
    é»İæĺİ
    0.20
    LER
    0.19
     travel
    0.19
    æĶ¶
    0.19
    éĻĢ
    0.19
    upy
    0.18
    马æĭīæĿ¾
    0.18
    scanf
    0.18
    Activations Density 0.002%

    No Known Activations