© 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. 29560
    Prev
    Next
    INDEX
    Explanations

    unwanted things

    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
    åIJĮæĦı
    -0.10
    æĹłéļľç¢į
    -0.10
    涸
    -0.09
    ãģŀ
    -0.09
    ured
    -0.09
    itant
    -0.09
    æĦıåij³çĿĢ
    -0.09
    éĶĻè¿ĩ
    -0.09
    æĢ»æķ°
    -0.09
     Hoy
    -0.09
    POSITIVE LOGITS
    ted
    0.09
     unwanted
    0.09
     surprises
    0.08
     веÑĩ
    0.08
    讫
    0.08
    é¦ĸåħĪæĺ¯
    0.08
    麻çĥ¦
    0.08
    /dist
    0.08
    orate
    0.08
    -too
    0.07
    Activations Density 0.009%

    No Known Activations