© 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. 63608
    Prev
    Next
    INDEX
    Explanations

    german articles and nouns

    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
    æīİæł¹
    -0.09
    è¾Ī
    -0.09
    åĪ¨
    -0.08
    è¾ŀ
    -0.08
    å°ĨåĨĽ
    -0.08
     Leben
    -0.08
    æ¿Ģèµ·
    -0.08
    icum
    -0.08
    size
    -0.08
    EOF
    -0.08
    POSITIVE LOGITS
    uppe
    0.09
    å¹³æĿ¿
    0.09
    liste
    0.08
    à¸Ļม
    0.08
    _COND
    0.08
    idence
    0.08
    orta
    0.08
    åĩĨåħ¥
    0.08
    é¢Ĩ导人
    0.08
    æݧ
    0.08
    Activations Density 0.021%

    No Known Activations