© 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. 13457
    Prev
    Next
    INDEX
    Explanations

    geographic regions and areas

    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
    å··
    -0.23
    ä¸İæĹ¶ä¿±è¿Ľ
    -0.21
    hợ
    -0.20
     Kunst
    -0.20
    åľ¨å½ĵåľ°
    -0.20
    è°·çĪ±
    -0.20
    åIJij社ä¼ļ
    -0.19
    schlü
    -0.19
    há»ķ
    -0.19
    éķĩæĶ¿åºľ
    -0.19
    POSITIVE LOGITS
     regions
    0.35
    éĥ¨åĪĨåľ°åĮº
    0.31
    åľ°åĮºçļĦ
    0.29
    åľ°åĮº
    0.27
    regions
    0.27
    ä¸Ģçīĩ
    0.25
    大çīĩ
    0.25
     areas
    0.25
    åľ°åįĢ
    0.24
    çľģ份
    0.24
    Activations Density 0.024%

    No Known Activations