© 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. 62116
    Prev
    Next
    INDEX
    Explanations

    legislative bodies and state 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
    åķĨéĩı
    -0.10
    梵
    -0.09
    èģĶéĤ¦
    -0.09
    å§ĭ
    -0.08
    aina
    -0.08
    æĺ¯ä¸ŃåĽ½
    -0.08
    æĺ¯æĪijåĽ½
    -0.08
    best
    -0.08
    å¤ĸ交éĥ¨
    -0.08
     cam
    -0.08
    POSITIVE LOGITS
    人家
    0.10
    å·ŀ
    0.10
     State
    0.09
    ä¸īä½į
    0.09
    æĥ©
    0.09
    _State
    0.09
    ogne
    0.09
    çħŀ
    0.09
    	State
    0.09
    èħ¹
    0.09
    Activations Density 0.343%

    No Known Activations