© 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. 15662
    Prev
    Next
    INDEX
    Explanations

    creators or groups described by actions

    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
    为éĩįçĤ¹
    -0.21
    æĢ»æķ°
    -0.21
    çļĦåŃĺåľ¨
    -0.18
    ä¸ºåŁºç¡Ģ
    -0.18
    ä¸Ńå°ıåŀĭ
    -0.18
    istle
    -0.18
     nal
    -0.18
    ç¥Ń
    -0.17
     vu
    -0.17
     REQ
    -0.17
    POSITIVE LOGITS
    /operator
    0.24
    èĢħ
    0.24
    åĪĿè¡·
    0.23
    lord
    0.22
    èĢħçļĦ
    0.21
    å¨ĺ
    0.21
     thereof
    0.20
     originally
    0.19
     Thousand
    0.19
    æľīæĦı
    0.19
    Activations Density 0.073%

    No Known Activations