© 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. 62877
    Prev
    Next
    INDEX
    Explanations

    Mediterranean and surrounding regions

    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
    é»ijé¾Ļæ±Łçľģ
    -0.11
    天津å¸Ĥ
    -0.10
    京津åĨĢ
    -0.10
     canada
    -0.10
    æľĿé²ľ
    -0.10
     Sioux
    -0.10
    秫
    -0.09
    åĵĪå°Ķ滨
    -0.09
    Canada
    -0.09
    èĥ¡åIJĮ
    -0.09
    POSITIVE LOGITS
     Mediterranean
    0.14
    åľ°ä¸Ńæµ·
    0.13
     Sic
    0.12
    å¸ĮèħĬ
    0.11
     olive
    0.11
     Greek
    0.11
    æ©Ħæ¦Ħ
    0.10
     Aless
    0.10
    Greek
    0.10
     Pis
    0.10
    Activations Density 0.155%

    No Known Activations