© 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. 11800
    Prev
    Next
    INDEX
    Explanations

    baseball hits

    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
    æĪijä¸įæĺ¯
    -0.18
    dy
    -0.18
    recur
    -0.18
    é¢ijéģĵ
    -0.18
    åĽºå®ļçļĦ
    -0.18
    .Imaging
    -0.18
    rica
    -0.18
    女ç¥ŀ
    -0.18
    calar
    -0.18
    .ibm
    -0.18
    POSITIVE LOGITS
    éĤĿ
    0.20
    erek
    0.18
    çĻ¾åĪĨä¹ĭ
    0.18
    æĮ½åĽŀ
    0.17
    æĿ¡ä»¶ä¸ĭ
    0.17
    大èĥĨ
    0.17
    nullptr
    0.17
    Ñģов
    0.17
    åħ¼
    0.17
    KS
    0.17
    Activations Density 0.001%

    No Known Activations