© 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. 29668
    Prev
    Next
    INDEX
    Explanations

    scam expert

    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
     заб
    -0.10
    htags
    -0.10
    £¼
    -0.10
    çĦ¶æĺ¯
    -0.10
    icot
    -0.09
     пÑĢавила
    -0.09
    elines
    -0.09
     tô
    -0.09
    åIJĦæł·
    -0.09
    è·ŁæĪij
    -0.09
    POSITIVE LOGITS
    gram
    0.09
    gle
    0.08
    STA
    0.08
    ä¼ŀ
    0.08
    ESS
    0.08
    gee
    0.08
    çĦĺ
    0.08
    ãĥĵãĤ¸
    0.08
    ulous
    0.08
     G
    0.08
    Activations Density 0.002%

    No Known Activations