© 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. 63840
    Prev
    Next
    INDEX
    Explanations

    break, broke, broken, breaking

    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
    URT
    -0.10
    被æīĵ
    -0.09
     Gors
    -0.09
    éĢ¡
    -0.09
    ÑĤÑģÑı
    -0.09
    éļ¾åº¦
    -0.09
    _UNDEF
    -0.09
     лиÑĪ
    -0.09
    ÑĢиÑģ
    -0.09
    å´®
    -0.08
    POSITIVE LOGITS
    ä¼Ļ
    0.10
     mainstream
    0.09
    æļ®
    0.08
    衲
    0.08
    主æµģ
    0.08
     negligent
    0.08
    éĿŀæ´²
    0.08
    åĴĮå®ĮåĸĦ
    0.08
    à¹Ģหà¸Ļ
    0.08
     scheme
    0.08
    Activations Density 0.007%

    No Known Activations