© 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. 5830
    Prev
    Next
    INDEX
    Explanations

    who is

    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
    æĺ¯ä¸Ģ项
    -0.10
    æ¿ij
    -0.09
    éķ¿æ±Ł
    -0.09
    æĺ¯ä¸Ģ件
    -0.09
    æĺ¯å¾Ī
    -0.09
     Consort
    -0.09
    åı«åģļ
    -0.09
    被称为
    -0.09
    æĺ¯ä¸ĢåIJį
    -0.09
     Malone
    -0.08
    POSITIVE LOGITS
    é¢Ħ
    0.09
    åģĩ
    0.09
    çĿ
    0.08
    骧
    0.08
    没äºĨ
    0.08
    MEA
    0.08
    ainer
    0.08
    ä½łèĥ½
    0.08
    YOU
    0.08
     fins
    0.08
    Activations Density 0.097%

    No Known Activations