© 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. 16256
    Prev
    Next
    INDEX
    Explanations

    variable, alongside, course, languages

    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
    æѤæĻĤ
    -0.22
    åľ¨æѤ
    -0.21
    igate
    -0.20
    è¿ĻæŶåĢĻ
    -0.20
    æѤæŶ
    -0.20
    è¿Ļ个æŶåĢĻ
    -0.20
    åľ¨æѤä¹ĭåīį
    -0.20
    è¿ĻéĩĮæĺ¯
    -0.19
    aminer
    -0.19
    æľ¬æĿ¥å°±
    -0.19
    POSITIVE LOGITS
    cr
    0.20
    oku
    0.20
    æį§
    0.19
    身ä¸Ĭ
    0.19
    ç½®
    0.18
    æĺ¼
    0.18
     span
    0.18
    åıĬåħ¶
    0.18
    è¿IJ
    0.18
    pure
    0.18
    Activations Density 0.402%

    No Known Activations