© 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. 32866
    Prev
    Next
    INDEX
    Explanations

    peace and peaceful life

    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
    æĪ¿ä¸ľ
    -0.11
    赶ä¸Ĭ
    -0.10
    æݧèĤ¡éĽĨåĽ¢
    -0.10
    鬲
    -0.09
     полÑĥ
    -0.09
    éĿ©æĸ°
    -0.09
    饯
    -0.09
    æ¶Ķ
    -0.09
    翻身
    -0.09
    æľ¬ç½ij
    -0.09
    POSITIVE LOGITS
     peace
    0.18
    Peace
    0.16
    å®īå®ģ
    0.16
     Peace
    0.16
    peace
    0.15
    å®ģéĿĻ
    0.15
    åĴĮå¹³
    0.14
    å¹³éĿĻ
    0.14
    åĴĮè°IJ
    0.12
     peaceful
    0.11
    Activations Density 0.041%

    No Known Activations