© 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. 63890
    Prev
    Next
    INDEX
    Explanations

    rock and roll

    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
    endet
    -0.09
    aland
    -0.09
    uchs
    -0.09
    Refreshing
    -0.08
    èĮ«
    -0.08
    润
    -0.08
    æľŁåĨħ
    -0.08
    Ø·ÙĪر
    -0.08
    figures
    -0.08
    沧
    -0.08
    POSITIVE LOGITS
    æ¿®
    0.09
    çĩ¥
    0.09
    efeller
    0.09
    åIJ®
    0.08
    å¶Ļ
    0.08
    æŃ£èĥ½éĩı
    0.08
     Vet
    0.08
    entials
    0.08
    姿åĬ¿
    0.08
    çĸµ
    0.08
    Activations Density 0.021%

    No Known Activations