© 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. 10962
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    andin
    -0.20
     Heard
    -0.19
    ç©Ĺ
    -0.19
     Hearing
    -0.19
    马ä¸Ĭ
    -0.18
     Suns
    -0.18
    -live
    -0.18
    oose
    -0.18
     Named
    -0.18
    .$.
    -0.18
    POSITIVE LOGITS
    OfType
    0.20
    æ¶Īæŀģ
    0.18
    å®ıè§Ĥç»ıæµİ
    0.18
    åįİ润
    0.17
    å®ıè§Ĥ
    0.17
    wake
    0.17
    ä¸įæ¸ħæ¥ļ
    0.17
    è¿Ļ个人
    0.17
    æŶ任
    0.17
    бли
    0.17
    Activations Density 0.000%

    No Known Activations