© 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. 3710
    Prev
    Next
    INDEX
    Explanations

    encourage, promote, support

    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
    å¾Ĺ罪
    -0.10
    红åĮħ
    -0.09
    èĥ½åģļåĪ°
    -0.09
    红楼
    -0.09
    ä¿Ŀåģ¥
    -0.08
    åı£æ°´
    -0.08
    æľ¬é¢Ĩ
    -0.08
    æ°¸æģĴ
    -0.08
    åݦ
    -0.08
     Neu
    -0.08
    POSITIVE LOGITS
    é¼ĵåĬ±
    0.14
    æī¶æĮģ
    0.13
    å¥
    0.13
    ä¿ĥè¿Ľ
    0.10
    å¼ķ导
    0.10
     discour
    0.10
    åĭ¤åĬ³
    0.10
    æ¿ĢåĬ±
    0.09
     incent
    0.09
     encouraging
    0.09
    Activations Density 0.056%

    No Known Activations