© 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. 48557
    Prev
    Next
    INDEX
    Explanations

    democracy and governance

    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
    èĩªç§ģ
    -0.09
    å¸ĪèµĦ
    -0.09
    éĺ´éĺ³
    -0.09
    amas
    -0.09
    çĴĭ
    -0.08
    ä¸ĢæŦ
    -0.08
    度è¿ĩ
    -0.08
    èķ¾
    -0.08
    è¿Ń
    -0.08
    å¦ĵ
    -0.08
    POSITIVE LOGITS
    æ°ij主
    0.25
     democracy
    0.22
     democratic
    0.19
     Democracy
    0.19
     Democr
    0.17
     democr
    0.17
    æ°ij主çĶŁæ´»
    0.14
    è®®äºĭ
    0.14
     Democratic
    0.13
    æ³ķæ²»
    0.13
    Activations Density 0.090%

    No Known Activations