© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 24326
    Prev
    Next
    INDEX
    Explanations

    New Year’s

    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
    Negative Logits
    å¥ģ
    -0.09
    亢
    -0.09
    å°ı康
    -0.09
    åħ¨æĹ¥
    -0.09
    äºĨä¸Ģéģį
    -0.09
    童年
    -0.09
    å¾Īå¼Ģå¿ĥ
    -0.09
    uns
    -0.09
    éĿ¢èī²
    -0.09
    å¿ĥåºķ
    -0.09
    POSITIVE LOGITS
    åĢĴ
    0.10
    çī¹åĪ«æĺ¯åľ¨
    0.09
    veau
    0.08
    ÙģÙĬÙĦ
    0.08
    .Sn
    0.08
    drive
    0.08
    ë¶ĢíĦ°
    0.08
    rait
    0.08
    imensional
    0.08
    affen
    0.08
    Activations Density 0.003%

    No Known Activations