© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 33236
    Prev
    Next
    INDEX
    Explanations

    locations and travel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    åľ¨æķ´ä¸ª
    -0.10
    è¡Įä¸ļåĨħ
    -0.09
    åľ¨å¤ĸéĿ¢
    -0.09
    Unmarshaller
    -0.09
    çĪ·
    -0.09
    åĩºè·¯
    -0.09
    èĩªå·±çļĦ
    -0.09
    è£ģ
    -0.08
    åľ¨åħ¶
    -0.08
    仪å¼ı
    -0.08
    POSITIVE LOGITS
    ä¹ĭæĹħ
    0.11
    访
    0.11
    訪
    0.10
    å¢ĥ
    0.10
    æĸĩåĮĸ交æµģ
    0.09
    访éĹ®
    0.09
    æľĭåıĭ
    0.09
    æĬ½
    0.09
     visit
    0.08
    访è°Ī
    0.08
    Activations Density 0.072%

    No Known Activations