© 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. 30112
    Prev
    Next
    INDEX
    Explanations

    C++ and C# programming languages

    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
    åħ«åŃĹ
    -0.11
    arus
    -0.09
    ICON
    -0.09
     Chapman
    -0.09
    éģ¿
    -0.08
    agar
    -0.08
     Bradley
    -0.08
    ç¦ı
    -0.08
    ä¼´
    -0.08
    аÑĢа
    -0.08
    POSITIVE LOGITS
    èį¦
    0.10
    çĦ
    0.10
    åľ¨å¤ĸéĿ¢
    0.10
    åĮĸçļĦ
    0.09
    udas
    0.09
    нÑıÑĤ
    0.09
    被åĬ¨
    0.09
    è¯Ńè¨Ģ
    0.08
    è°Ľ
    0.08
    -language
    0.08
    Activations Density 0.352%

    No Known Activations