© 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. 11003
    Prev
    Next
    INDEX
    Explanations

    Philippines, Manila, actor

    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
    ä¸Ģçľ¼
    -0.09
    åijµ
    -0.09
    æĭĽåij¼
    -0.09
    èIJ¥
    -0.08
    ä¾Ľç»Ļ
    -0.08
    æłĸ
    -0.08
    izr
    -0.08
     fla
    -0.08
    âĩ¨
    -0.08
    ç«
    -0.07
    POSITIVE LOGITS
     Manila
    0.11
    溪
    0.11
    å§Ķç»Ħç»ĩ
    0.10
    æ¦ķ
    0.09
    èı²å¾ĭ宾
    0.09
    upro
    0.09
    åĪĹ为
    0.09
    éĴī
    0.09
    对æİ¥
    0.09
    éĢµ
    0.09
    Activations Density 0.141%

    No Known Activations