© 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. 19177
    Prev
    Next
    INDEX
    Explanations

    ocean, sea, rivers, water bodies

    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
    çĻ½è¡£
    -0.10
    æ¸ħé¦Ļ
    -0.09
    èĬ·
    -0.09
    鼷æĸ¯
    -0.09
     skÅĤad
    -0.09
    åħĥ
    -0.09
    æĸĻ
    -0.08
    å²ij
    -0.08
    ä¿Ŀå®ī
    -0.08
    çīĮçħ§
    -0.08
    POSITIVE LOGITS
    æ°´åŁŁ
    0.14
    æ°´éĿ¢
    0.13
    æ²³æµģ
    0.13
    ä¸Ģåı£
    0.11
    utow
    0.11
     sông
    0.11
     water
    0.11
     водо
    0.11
    æ°´ä¸Ń
    0.11
    æ¹ĸæ³Ĭ
    0.10
    Activations Density 0.116%

    No Known Activations