© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 16971
    Prev
    Next
    INDEX
    Explanations

    Florida courts and legal documents

    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
     Tibet
    -0.28
     Mongolia
    -0.26
    éĥ«
    -0.25
    éĿĴæµ·
    -0.24
    æģ©æĸ½
    -0.23
    西å®ģ
    -0.23
    éĿĴæµ·çľģ
    -0.23
     Kami
    -0.22
     Omaha
    -0.21
    èĥ¡åIJĮ
    -0.21
    POSITIVE LOGITS
     Florida
    0.57
    Florida
    0.54
     Tampa
    0.47
     Miami
    0.46
    åľ¨æ·±åľ³
    0.46
    Miami
    0.43
    æ·±åľ³å¸Ĥ
    0.41
    æ·±åľ³
    0.40
    çĥŃ带
    0.38
     Fla
    0.35
    Activations Density 0.342%

    No Known Activations