© 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. 19409
    Prev
    Next
    INDEX
    Explanations

    jewish identity and culture

    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
    ingly
    -0.09
    累累
    -0.08
    ément
    -0.08
     ÑģоÑĨиалÑĮно
    -0.08
    鸡èĽĭ
    -0.08
    ament
    -0.07
    esthesia
    -0.07
    gee
    -0.07
    adic
    -0.07
    å·¢
    -0.07
    POSITIVE LOGITS
    ness
    0.14
    _NOW
    0.11
    è¿Ļ对
    0.11
    keit
    0.10
    atten
    0.10
    zelf
    0.10
    åIJĮèĥŀ
    0.10
    ãģĿãģĨãģª
    0.10
    NESS
    0.09
    кÑĥÑģ
    0.09
    Activations Density 0.005%

    No Known Activations