© 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. 23375
    Prev
    Next
    INDEX
    Explanations

    defense secretary

    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
    祢
    -0.09
    éľģ
    -0.09
    è¿ĺä¼ļ
    -0.09
    èµĥ
    -0.09
     СÑĤа
    -0.09
    管çIJĨå·¥ä½ľ
    -0.09
    é¢Ħè¨Ģ
    -0.09
    ãĢĴ
    -0.08
    äºĨåIJ§
    -0.08
    mock
    -0.08
    POSITIVE LOGITS
    åĨĽéĺŁ
    0.13
    è®®
    0.11
    åĨĽäºĭ
    0.11
     обоÑĢ
    0.10
    æĪĺæĸĹåĬĽ
    0.10
    åı¸ä»¤
    0.10
    ilit
    0.10
    åĨĽäºº
    0.10
    æŀķ
    0.09
    æĮĩæĮ¥
    0.09
    Activations Density 0.110%

    No Known Activations