© 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. 22810
    Prev
    Next
    INDEX
    Explanations

    Philippines and cities

    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
    ä½Ļ家
    -0.10
    èııæ³½
    -0.10
    èĿĪ
    -0.10
    íıŃ
    -0.09
    ç¿İ
    -0.09
    èĻ¢
    -0.09
    åŃĹåı·
    -0.09
    éĥĵ
    -0.08
    æĺ¨å¤©
    -0.08
    åĨĽå·¥
    -0.08
    POSITIVE LOGITS
     Filipino
    0.13
    èı²å¾ĭ宾
    0.12
     Singapore
    0.12
    æĸ°åĬłåĿ¡
    0.12
    ç¦ı建çľģ
    0.12
    æ³īå·ŀ
    0.12
    éĹ½
    0.11
    Singapore
    0.11
     Manila
    0.11
     Malay
    0.11
    Activations Density 0.260%

    No Known Activations