© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12399
    Prev
    Next
    INDEX
    Explanations

    season and fall clothing collections

    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
    Disposed
    -0.20
     беÑģплаÑĤ
    -0.19
    íķĺëıĦë¡Ŀ
    -0.19
    ãģ¨ãģĹãģ¦ãĤĤ
    -0.19
    istory
    -0.19
    .ContentType
    -0.19
    à°³
    -0.18
    åįĬå°ıæŶ
    -0.18
    onden
    -0.18
    ä¿Ŀåģ¥
    -0.18
    POSITIVE LOGITS
     season
    0.29
    æĸ°åĵģ
    0.29
    season
    0.29
    åŃ£
    0.25
    åŃ£èĬĤ
    0.25
    主æīĵ
    0.24
     seasons
    0.21
    åºŁçī©
    0.21
    Season
    0.20
    æĸ°æ¬¾
    0.20
    Activations Density 0.011%

    No Known Activations