© 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. 20615
    Prev
    Next
    INDEX
    Explanations

    Copyright and Java licenses

    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
    (exports
    -0.09
    .Migrations
    -0.08
    ês
    -0.08
    åĤ¨åŃĺ
    -0.08
    滦
    -0.08
    åĽŀæĬ¥
    -0.08
    ä¸įåıĬ
    -0.07
    <?=
    -0.07
    æĺ¼å¤ľ
    -0.07
     PDO
    -0.07
    POSITIVE LOGITS
    _java
    0.13
    .java
    0.12
    java
    0.12
     java
    0.12
    javax
    0.12
    .jav
    0.12
     Java
    0.12
     javax
    0.12
    .spi
    0.11
    	java
    0.11
    Activations Density 2.990%

    No Known Activations