© 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. 27398
    Prev
    Next
    INDEX
    Explanations

    Greek and Greece

    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
    æĸ¡
    -0.09
    isci
    -0.09
    .dy
    -0.08
    æĪķ
    -0.08
     corpus
    -0.08
    éĢIJ
    -0.08
     Sinatra
    -0.08
    åĻ¨å®ĺ
    -0.08
    å¹²äºĭ
    -0.08
     Skull
    -0.08
    POSITIVE LOGITS
    å¸ĮèħĬ
    0.17
     Greek
    0.17
    Greek
    0.14
    表åĨ³
    0.12
     Greece
    0.12
     Athens
    0.12
     Greeks
    0.12
     Athen
    0.12
    åħ¬åħĥåīį
    0.11
    å®Ļ
    0.09
    Activations Density 0.083%

    No Known Activations