© 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. 22809
    Prev
    Next
    INDEX
    Explanations

    Malaysia and its specific places

    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
    仡
    -0.09
    èĥ½çľĭåĩº
    -0.09
    综
    -0.08
    åIJİéĿ¢çļĦ
    -0.08
    ä¸Ģç»ı
    -0.08
    ä¿Ħ
    -0.08
    åIJİéĿ¢
    -0.08
    ä¸Ģ声
    -0.08
    ç®Ģ
    -0.08
    åľ¨å½ĵåľ°
    -0.08
    POSITIVE LOGITS
     Malaysia
    0.11
    æĿª
    0.11
    马æĿ¥
    0.11
     Malaysian
    0.11
    åı»
    0.10
     Kuala
    0.10
    马æĿ¥è¥¿äºļ
    0.09
    æ§Ł
    0.09
    åĶĶ
    0.09
    èľļ
    0.09
    Activations Density 0.252%

    No Known Activations