© 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. 6002
    Prev
    Next
    INDEX
    Explanations

    piston engine

    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
    é¢ī
    -0.11
    liness
    -0.11
    orris
    -0.10
    ings
    -0.10
    稷
    -0.09
    åİ¢
    -0.09
    åĿŀ
    -0.09
    ording
    -0.09
    еÑĢÑĤ
    -0.08
    å©¿
    -0.08
    POSITIVE LOGITS
    <<<<
    0.11
    /or
    0.10
    ieri
    0.10
    eur
    0.09
    ted
    0.09
    crit
    0.09
    errat
    0.09
    ä¸ĭéĿ¢æĺ¯
    0.09
    鬯
    0.09
    ently
    0.09
    Activations Density 0.020%

    No Known Activations