© 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. 13281
    Prev
    Next
    INDEX
    Explanations

    get or understand

    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
    çľĭæľĽ
    -0.22
    åı¯è§Ĥ
    -0.20
    豫
    -0.20
    é£İæ³¢
    -0.20
    çijķçĸµ
    -0.18
    æĸĹ
    -0.18
    ä¹ĭ称
    -0.18
    åĽŀæĥ³
    -0.17
    æ¶Īæģ¯ç§°
    -0.17
     внимание
    -0.17
    POSITIVE LOGITS
    çIJĨ解
    0.40
    é¢Ĩä¼ļ
    0.35
     understanding
    0.32
    çļĦçIJĨ解
    0.30
     why
    0.30
    æĺİçĻ½
    0.29
     comprend
    0.28
     Understanding
    0.28
     understands
    0.28
    Understanding
    0.28
    Activations Density 0.074%

    No Known Activations