© 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. 14149
    Prev
    Next
    INDEX
    Explanations

    tech and .com domains

    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
    åĪ°åºķæĺ¯
    -0.20
    é»ı
    -0.19
    æ¿¡
    -0.18
    åĪį
    -0.18
    é«ĺæīĭ
    -0.18
     cocina
    -0.18
    ç²¾å¿ĥ
    -0.18
    ä¸Ģ大åłĨ
    -0.17
    mente
    -0.17
     cass
    -0.17
    POSITIVE LOGITS
    éĴ¿
    0.21
    antu
    0.20
     Mister
    0.20
    etch
    0.19
    apa
    0.19
    apas
    0.18
    Hum
    0.18
    å®ļå¾ĭ
    0.18
    ä»Ģ
    0.18
    è¯Ģ
    0.18
    Activations Density 0.008%

    No Known Activations