© 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. 13744
    Prev
    Next
    INDEX
    Explanations

    Finnish, Finland, Helsinki

    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
    京津åĨĢ
    -0.23
    åĨĢ
    -0.22
    led
    -0.22
     NYPD
    -0.22
    å¤Ķ
    -0.21
    æ½ŀ
    -0.21
    æ»ı
    -0.21
    anzi
    -0.20
    isco
    -0.19
     Bronx
    -0.19
    POSITIVE LOGITS
    èĬ¬åħ°
    0.49
     Finnish
    0.48
     Finland
    0.44
     Helsinki
    0.40
     Estonia
    0.31
    é»ijé¾Ļæ±Łçľģ
    0.30
    elsinki
    0.29
    çĵ¯
    0.28
     Eston
    0.28
    .fi
    0.27
    Activations Density 0.136%

    No Known Activations