© 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. 13022
    Prev
    Next
    INDEX
    Explanations

    philosophy and philosophical topics

    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
    _tpl
    -0.22
    .geom
    -0.21
    æĮĩæłĩ
    -0.20
    -caption
    -0.20
    è§ĦåĪĴ设计
    -0.20
     MANUAL
    -0.19
    åĪ°æĿ¥
    -0.19
     диÑĢ
    -0.19
    管çIJĨæĿ¡ä¾ĭ
    -0.19
     blat
    -0.19
    POSITIVE LOGITS
     philosophers
    0.28
     philosopher
    0.27
     Kant
    0.25
    辩æĬ¤
    0.24
     argued
    0.23
    论è¯ģ
    0.23
     qua
    0.23
     Witt
    0.23
     philosophical
    0.23
     arguments
    0.22
    Activations Density 0.087%

    No Known Activations