© 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. 15335
    Prev
    Next
    INDEX
    Explanations

    decide whether

    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
    çIJĨ解åĴĮ
    -0.19
    .getParameter
    -0.19
    çĽijå¯Ł
    -0.18
    еÑĨ
    -0.18
    æ¸ł
    -0.18
    精彩
    -0.18
    çĽijçIJĨ
    -0.18
    æºIJæºIJ
    -0.18
    ä¸įæĸŃåıijå±ķ
    -0.18
    çĽij
    -0.18
    POSITIVE LOGITS
    æĺ¯åIJ¦ä¼ļ
    0.40
     whether
    0.40
    æĺ¯åIJ¦
    0.39
     Whether
    0.33
    whether
    0.32
     WHETHER
    0.31
    Whether
    0.31
    æĺ¯åIJ¦æľī
    0.30
    æĺ¯åIJ¦åŃĺåľ¨
    0.30
    åĪ°åºķæĺ¯
    0.30
    Activations Density 0.080%

    No Known Activations