© 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. 11586
    Prev
    Next
    INDEX
    Explanations

    insults towards people

    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
    äºĨ解ä¸Ģä¸ĭ
    -0.10
    leys
    -0.09
    çĥŃ度
    -0.08
    åħ¸
    -0.08
    Ñĩа
    -0.08
    é»ĦçŁ³
    -0.08
    -Sah
    -0.08
    ponsored
    -0.08
    çĸ¯
    -0.08
    ä¸¥æł¼
    -0.08
    POSITIVE LOGITS
    æīĩ
    0.10
    äººæł¼
    0.09
    _TI
    0.09
    é¼»åŃIJ
    0.09
    ä½łèĩªå·±
    0.09
    æ°´å¹³
    0.09
    ew
    0.09
    ç½µ
    0.09
    笨
    0.09
     irr
    0.08
    Activations Density 0.059%

    No Known Activations