© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22151
    Prev
    Next
    INDEX
    Explanations

    library and research materials

    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
    åIJįå½ķ
    -0.10
    è®®
    -0.09
    åŁºè°ĥ
    -0.09
    模ç³Ĭ
    -0.08
     bottom
    -0.08
    讲å¸Ī
    -0.08
    鲤
    -0.08
    æĭĮ
    -0.08
     dish
    -0.08
    åľ°å¸¦
    -0.08
    POSITIVE LOGITS
    åĽ¾ä¹¦é¦Ĩ
    0.20
    éĺħè§Ī
    0.15
    é¦Ĩ
    0.15
     library
    0.15
    .library
    0.15
    åĽ¾ä¹¦
    0.14
    Collections
    0.13
    /library
    0.13
    Library
    0.13
    library
    0.13
    Activations Density 0.075%

    No Known Activations