© 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. 6047
    Prev
    Next
    INDEX
    Explanations

    relative clauses starting with which

    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
    æĢ§å¼º
    -0.11
    stim
    -0.10
    è¿Ļäºĭ
    -0.09
    åĬłå¼ºå¯¹
    -0.09
     stim
    -0.09
    æĤ¬
    -0.09
    pret
    -0.09
    è¯Ŀ说
    -0.09
    åĿļ强
    -0.08
    åĪºæ¿Ģ
    -0.08
    POSITIVE LOGITS
    lops
    0.09
    æĺ¯æ²¡æľī
    0.08
    loi
    0.08
    loff
    0.08
    reib
    0.08
    墨
    0.08
    æĢ»
    0.07
    opper
    0.07
    cca
    0.07
    cents
    0.07
    Activations Density 0.035%

    No Known Activations