© 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. 52608
    Prev
    Next
    INDEX
    Explanations

    young actors and celebrities

    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
    çļĦ女人
    -0.09
    ä¾ł
    -0.09
    woman
    -0.09
    rum
    -0.09
    女人
    -0.09
    ä¸Ī夫
    -0.08
    women
    -0.08
     Nursing
    -0.08
    Ķ
    -0.08
    Women
    -0.08
    POSITIVE LOGITS
    ç¨ļ
    0.15
    åŃ©ç«¥
    0.13
    éĿĴå°ijå¹´
    0.13
    æľªæĪIJå¹´
    0.13
    åĦ¿ç«¥
    0.13
    年纪
    0.12
    女åŃ©
    0.12
    å°ijå¹´
    0.12
    å¹´é¾Ħ
    0.12
    ç«¥
    0.12
    Activations Density 0.092%

    No Known Activations