© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 32884
    Prev
    Next
    INDEX
    Explanations

    adverse side effects

    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
    åĭł
    -0.09
    代åĬŀ
    -0.09
    é¼İ
    -0.08
    æľīæĦıæĢĿ
    -0.08
    æ°´åŁŁ
    -0.08
    çĥŁåĽ±
    -0.08
    éĥħ
    -0.08
    æĽ¿
    -0.08
    æĺŃ
    -0.08
    å¼Ģè¾Ł
    -0.08
    POSITIVE LOGITS
    åī¯ä½ľçĶ¨
    0.12
    ãĤ·ãĤ§
    0.09
    .lift
    0.09
    误导
    0.09
     Benn
    0.09
    襲
    0.08
    elfare
    0.08
    -muted
    0.08
    è¢Ń
    0.08
    æ»Ł
    0.08
    Activations Density 0.080%

    No Known Activations