© 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. 33956
    Prev
    Next
    INDEX
    Explanations

    lua language

    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
    å½Ŀ
    -0.10
    æµı
    -0.09
    æĪIJéĥ½å¸Ĥ
    -0.09
     Borough
    -0.09
    æĺ¯éŁ©åĽ½
    -0.09
     tempting
    -0.08
    æ¿ĢçĥĪçļĦ
    -0.08
    éĿ³
    -0.08
     Newark
    -0.08
    åĽĽå·Ŀ
    -0.08
    POSITIVE LOGITS
    .lua
    0.18
     Lua
    0.16
    Lua
    0.15
    (lua
    0.15
    _lua
    0.13
     LUA
    0.13
     lua
    0.13
    lua
    0.12
    	lua
    0.11
     ipairs
    0.11
    Activations Density 0.092%

    No Known Activations