© 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. 16113
    Prev
    Next
    INDEX
    Explanations

    tell you

    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
    人æ°ijæľįåĬ¡
    -0.24
    éŀĺ
    -0.22
    оÑĤов
    -0.22
     подпиÑģ
    -0.22
    éĴ¿
    -0.18
    妥
    -0.18
     ÙħÙĨÙĩا
    -0.18
    çº
    -0.18
    éĢĤåIJĪèĩªå·±
    -0.18
    ddy
    -0.18
    POSITIVE LOGITS
    åĩłåı¥
    0.20
     about
    0.20
    æĪij对
    0.20
    å¦Ĥæŀľä½ł
    0.19
    IW
    0.19
    æĪijçİ°åľ¨
    0.19
    åł°
    0.18
    åıijçĶŁäºĨ
    0.18
    .jp
    0.18
    åħ³åı£
    0.18
    Activations Density 0.012%

    No Known Activations