© 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. 58426
    Prev
    Next
    INDEX
    Explanations

    question words followed by auxiliary verbs

    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
    æĸ¹æīį
    -0.09
    wer
    -0.08
    们
    -0.08
    ä¸įæķ¢
    -0.08
    irse
    -0.08
    å¾¼
    -0.08
     ||
    -0.08
    WAIT
    -0.08
    å¾Īå¥½åľ°
    -0.08
     Gol
    -0.08
    POSITIVE LOGITS
    æĺ¯åľ¨
    0.11
     does
    0.10
    ãģ¯
    0.10
     did
    0.10
    äºĨåIJĹ
    0.10
    Õŀ
    0.10
    æĺ¯ä½ł
    0.10
     are
    0.10
    á»ĩu
    0.10
    æĺ¯æĪij们
    0.09
    Activations Density 0.113%

    No Known Activations