© 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. 5963
    Prev
    Next
    INDEX
    Explanations

    Jenkins CI pipeline build

    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
    æľ¬èĥ½
    -0.10
    åĥŃ
    -0.09
    modifiable
    -0.09
    è¾Ĺ转
    -0.09
    æĪIJ年人
    -0.09
    å¤ķéĺ³
    -0.09
    udas
    -0.09
    模èĮĥ
    -0.09
    ç«ĭæ¡Ī
    -0.09
    ä¸įåı¯æĢĿ
    -0.09
    POSITIVE LOGITS
    enkins
    0.10
    coverage
    0.10
     ding
    0.09
    erge
    0.09
     Titanium
    0.09
    æĴŃæĬ¥
    0.09
     Jenkins
    0.08
    æµĩ
    0.08
    涵
    0.08
    _triggered
    0.08
    Activations Density 0.368%

    No Known Activations