© 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. 13004
    Prev
    Next
    INDEX
    Explanations

    award names

    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
    ayas
    -0.22
     surreal
    -0.21
    alem
    -0.21
    éĿĴå°ijå¹´
    -0.20
     amateur
    -0.20
    .sd
    -0.19
     underage
    -0.19
    注åĨĮ
    -0.19
    èķī
    -0.19
    dn
    -0.19
    POSITIVE LOGITS
    天天
    0.28
    让åѦçĶŁ
    0.25
    æ¯ı天éĥ½
    0.24
    讲æķħäºĭ
    0.24
    å°Ĩ士
    0.23
     пÑĥÑĤеÑĪ
    0.23
    çıŃ级
    0.23
    é«ĺæķĪ
    0.22
    让ä»ĸ们
    0.22
    å¤įä¹ł
    0.22
    Activations Density 0.037%

    No Known Activations