© 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. 34800
    Prev
    Next
    INDEX
    Explanations

    April Fool's Day prank calls

    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
    容纳
    -0.10
    etect
    -0.10
    forced
    -0.09
    满æĦı
    -0.09
    çݦ
    -0.09
    æĸ©
    -0.09
    çIJ³
    -0.09
    å¾Ī满æĦı
    -0.09
    ucer
    -0.09
     prostitution
    -0.09
    POSITIVE LOGITS
     prank
    0.20
    çİ©ç¬ij
    0.15
    å¹½é»ĺ
    0.13
    ç¬ijè¯Ŀ
    0.13
    æĪı
    0.12
    çĮ¾
    0.10
    æ¸ħæĺİ
    0.10
     joke
    0.09
    è°ĥä¾ĥ
    0.09
    å¼Ģçİ©ç¬ij
    0.09
    Activations Density 0.091%

    No Known Activations