© 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. 14828
    Prev
    Next
    INDEX
    Explanations

    long, delighted, and timely statements

    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
    åĩŃè¯ģ
    -0.19
     Bold
    -0.19
    æĤĦ
    -0.19
    æĬĢæľ¯æľįåĬ¡
    -0.18
     Newtown
    -0.18
    éļIJéļIJ
    -0.18
    ä¹ŁåĽłæѤ
    -0.17
    Constraint
    -0.17
    ä¸Ģ举
    -0.17
    宾客
    -0.17
    POSITIVE LOGITS
    çļĦç¡®æĺ¯
    0.23
    udder
    0.19
    çľĭå¾Ĺ
    0.18
     endorse
    0.18
    irá
    0.18
    çļĦç¡®
    0.18
    _ED
    0.17
    Blake
    0.17
    OMATIC
    0.17
    upy
    0.17
    Activations Density 0.046%

    No Known Activations