© 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. 29744
    Prev
    Next
    INDEX
    Explanations

    contact for information

    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
    èĮĥ
    -0.10
    ÙĪات
    -0.09
    éĢĭ
    -0.08
    arez
    -0.08
    åīĮ
    -0.08
    uar
    -0.08
    owner
    -0.08
    æ²ī
    -0.08
    ä¸ĢæĬĬ
    -0.08
     ebooks
    -0.08
    POSITIVE LOGITS
    æľ¬æ¬¡
    0.11
    æľ¬æ¬¡æ´»åĬ¨
    0.10
    童年
    0.09
    å®ŀåľ°
    0.09
    æ·»
    0.09
    æĺİåªļ
    0.09
    人们对
    0.09
    æŃ¤æ¬¡
    0.08
    å¿ĥçIJĨåѦ
    0.08
    å°ļ
    0.08
    Activations Density 0.004%

    No Known Activations