© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36723
    Prev
    Next
    INDEX
    Explanations

    java and programming language keywords

    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
     NGX
    -0.10
    éĻĩ
    -0.09
    ä¸Ģç»ı
    -0.09
    æ·±åĮĸ
    -0.08
    (global
    -0.08
    gle
    -0.08
    硬åĮĸ
    -0.08
    襦
    -0.08
     ItemType
    -0.08
     vg
    -0.08
    POSITIVE LOGITS
    .jav
    0.16
     java
    0.15
    /jav
    0.15
    java
    0.15
    (java
    0.14
    .java
    0.14
     Java
    0.13
    	java
    0.13
    Java
    0.12
     javafx
    0.12
    Activations Density 2.095%

    No Known Activations